research paper on chatgpt

Information

• Author Services

Initiatives

You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader.

All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess .

Feature papers represent the most advanced research with significant potential for high impact in the field. A Feature Paper should be a substantial original Article that involves several techniques or approaches, provides an outlook for future research directions and describes possible research applications.

Feature papers are submitted upon individual invitation or recommendation by the scientific editors and must receive positive feedback from the reviewers.

Editor’s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.

Original Submission Date Received: .

• Active Journals
• Find a Journal
• Proceedings Series
• For Authors
• For Reviewers
• For Editors
• For Librarians
• For Publishers
• For Societies
• For Conference Organizers
• Open Access Policy
• Institutional Open Access Program
• Special Issues Guidelines
• Editorial Process
• Research and Publication Ethics
• Article Processing Charges
• Testimonials
• Preprints.org
• SciProfiles
• Encyclopedia

Article Menu

• Subscribe SciFeed
• Recommended Articles
• Author Biographies
• Google Scholar
• on Google Scholar
• Table of Contents

Find support for a specific problem in the support section of our website.

Please let us know what you think of our products and services.

Visit our dedicated information section to learn more about MDPI.

JSmol Viewer

A comprehensive study of chatgpt: advancements, limitations, and ethical considerations in natural language processing and cybersecurity.

1. Introduction

1.1. motivation, 1.2. main contribution of this paper, 1.3. paper organization, 2. related work, 3. an overview of chatgpt.

• The input layer takes in a sequence of words and converts them into numerical representations called embeddings. The embeddings are passed to the transformer layers.
• The transformer layers are made up of multi-head self-attention mechanisms and feed-forward neural networks. The self-attention mechanisms allow the model to focus on specific parts of the input when generating a response, while the feed-forward neural networks allow the model to learn and extract features from the input.
• The transformer layers are stacked on top of each other and are connected through residual connections. This allows the model to learn and extract features at different levels of abstraction.

4. A Comparative Study of ChatGPT and Other Language Generation Models

• Language generation: GPT-3 has been found to generate more fluent and natural-sounding language than BERT in several studies. This is likely due to GPT-3’s larger model size and training data, which allows it to capture more nuanced relationships between words and phrases [ 23 ].
• Question answering: GPT-3 has been found to be more accurate than BERT in answering questions based on a given context. This is likely due to GPT-3’s ability to generate text, which allows it to provide more detailed and informative answers [ 25 ].
• Text generation: GPT-3 has been found to generate more coherent and coherently written text than BERT in several studies. This is likely due to GPT-3’s ability to generate text, which allows it to generate more complete and well-formed sentences [ 26 ].
• Text completion: GPT-3 has been found to be more accurate than BERT in completing the text, especially in the case of long-form text such as articles and essays [ 27 ].
• Summarization: GPT-3 has been found to generate more fluent and informative summaries than BERT in several studies. This is likely due to GPT-3’s ability to understand and analyze the content of a text, which allows it to generate more accurate and informative summaries [ 13 , 28 ].
• Sentiment analysis: GPT-3 has been found to be more accurate than BERT in determining the sentiment of text, such as whether the text expresses a positive, negative, or neutral sentiment [ 29 ].
• Text classification: GPT-3 has been found to be more accurate than BERT in classifying text into different categories, such as news articles, social media posts, and customer reviews [ 30 ].
• Dialogue systems: GPT-3 has been found to be more accurate than BERT in generating natural and coherent responses in dialogue systems such as chatbots [ 31 ].

5. ChatGPT for Dialogue Generation

6. chatgpt and privacy concerns: an analysis, 7. chatgpt and its applications in business and industry, 8. training and fine tuning chatgpt for specific tasks.

8.1. Fine Tuning ChatGPT for Text Summarization

8.2. fine tuning chatgpt for question answering, 9. language generation quality, 10. evaluating the performance of chatgpt on different languages and domains, 11. chatgpt in cybersecurity, 12. the future of chatgpt, 12.1. limitations of chatgpt, 12.2. research trends, 13. conclusions, author contributions, institutional review board statement, data availability statement, conflicts of interest.

• Zong, M.; Krishnamachari, B. A survey on GPT-3. arXiv 2022 , arXiv:2212.00857. [ Google Scholar ] [ CrossRef ]
• Kasneci, E.; Sessler, K.; Küchemann, S.; Bannert, M.; Dementieva, D.; Fischer, F.; Gasser, U.; Groh, G.; Günnemann, S.; Hüllermeier, E.; et al. ChatGPT for good? On opportunities and challenges of large language models for education. Learn. Individ. Differ. 2023 , 103 , 102274. [ Google Scholar ] [ CrossRef ]
• Sobieszek, A.; Price, T. Playing games with ais: The limits of gpt-3 and similar large language models. Minds Mach. 2022 , 32 , 341–364. [ Google Scholar ] [ CrossRef ]
• Floridi, L.; Chiriatti, M. GPT-3: Its nature, scope, limits, and consequences. Minds Mach. 2020 , 30 , 681–694. [ Google Scholar ] [ CrossRef ]
• Wenzlaff, K.; Spaeth, S. Smarter Than Humans? Validating How OpenAI’s ChatGPT Model Explains Crowdfunding, Alternative Finance and Community Finance ; Universitat Hamburg: Hamburg, Germay, 2022. [ Google Scholar ]
• DEMİR, Ş.Ş.; DEMİR, M. Professionals’ perspectives on ChatGPT in the tourism industry: Does it inspire awe or concern? J. Tour. Theory Res. 2023 , 9 , 61–76. [ Google Scholar ] [ CrossRef ]
• Vaishya, R.; Misra, A.; Vaish, A. ChatGPT: Is this version good for healthcare and research? Diabetes Metab. Syndr. Clin. Res. Rev. 2023 , 17 , 102744. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Ray, P.P. ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet Things Cyber-Phys. Syst. 2023 , 3 , 121–154. [ Google Scholar ] [ CrossRef ]
• Bhattaram, S.; Shinde, V.S.; Khumujam, P.P. ChatGPT: The next-gen tool for triaging? Am. J. Emerg. Med. 2023 , 69 , 215–217. [ Google Scholar ] [ CrossRef ]
• Wu, T.; He, S.; Liu, J.; Sun, S.; Liu, K.; Han, Q.L.; Tang, Y. A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development. IEEE/CAA J. Autom. Sin. 2023 , 10 , 1122–1136. [ Google Scholar ] [ CrossRef ]
• Van Dis, E.A.; Bollen, J.; Zuidema, W.; van Rooij, R.; Bockting, C.L. ChatGPT: Five priorities for research. Nature 2023 , 614 , 224–226. [ Google Scholar ] [ CrossRef ]
• Lin, W.; Tseng, B.H.; Byrne, B. Knowledge-aware graph-enhanced gpt-2 for dialogue state tracking. arXiv 2021 , arXiv:2104.04466. [ Google Scholar ] [ CrossRef ]
• Goyal, T.; Li, J.J.; Durrett, G. News Summarization and Evaluation in the Era of GPT-3. arXiv 2022 , arXiv:2209.12356. [ Google Scholar ] [ CrossRef ]
• Gilson, A.; Safranek, C.W.; Huang, T.; Socrates, V.; Chi, L.; Taylor, R.A.; Chartash, D. How does CHATGPT perform on the United States Medical Licensing Examination? the implications of large language models for medical education and knowledge assessment. JMIR Med. Educ. 2023 , 9 , e45312. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, L.; Polosukhin, I. Attention is all you need. In Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, 4–9 December 2017; Volume 30.
• Azaria, A. ChatGPT Usage and Limitations. In Proceedings of the 45th Annual Meeting of the Cognitive Science Society, Sydney, Australia, 26–29 July 2023; Available online: https://hal.science/hal-03913837/ (accessed on 12 August 2023).
• Mars, M. From Word Embeddings to Pre-Trained Language Models: A State-of-the-Art Walkthrough. Appl. Sci. 2022 , 12 , 8805. [ Google Scholar ] [ CrossRef ]
• Liu, P.; Yuan, W.; Fu, J.; Jiang, Z.; Hayashi, H.; Neubig, G. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 2023 , 55 , 1–35. [ Google Scholar ] [ CrossRef ]
• Fröhling, L.; Zubiaga, A. Feature-based detection of automated language models: Tackling GPT-2, GPT-3 and Grover. PeerJ Comput. Sci. 2021 , 7 , e443. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Liu, X.; Yin, D.; Zheng, J.; Zhang, X.; Zhang, P.; Yang, H.; Dong, Y.; Tang, J. Oag-bert: Towards a unified backbone language model for academic knowledge services. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, 14–18 August 2022; pp. 3418–3428. [ Google Scholar ]
• Meyer, S.; Elsweiler, D.; Ludwig, B.; Fernandez-Pichel, M.; Losada, D.E. Do We Still Need Human Assessors? Prompt-Based GPT-3 User Simulation in Conversational AI. In Proceedings of the 4th Conference on Conversational User Interfaces, Glasgow, UK, 26–28 July 2022; pp. 1–6. [ Google Scholar ]
• Lee, J.S.; Hsiang, J. Patent classification by fine-tuning BERT language model. World Pat. Inf. 2020 , 61 , 101965. [ Google Scholar ] [ CrossRef ]
• Li, Q.; Peng, H.; Li, J.; Xia, C.; Yang, R.; Sun, L.; Yu, P.S.; He, L. A survey on text classification: From shallow to deep learning. arXiv 2020 , arXiv:2008.00364. [ Google Scholar ] [ CrossRef ]
• Sun, C.; Qiu, X.; Xu, Y.; Huang, X. How to fine-tune bert for text classification? In Proceedings of the China National Conference on Chinese Computational Linguistics, Kunming, China, 18–20 October 2019; Springer: Cham, Switzerland, 2019; pp. 194–206. [ Google Scholar ]
• Yang, Z.; Gan, Z.; Wang, J.; Hu, X.; Lu, Y.; Liu, Z.; Wang, L. An empirical study of gpt-3 for few-shot knowledge-based vqa. Proc. Proc. Aaai Conf. Artif. Intell. 2022 , 36 , 3081–3089. [ Google Scholar ] [ CrossRef ]
• Zhang, Y.; Sun, S.; Gao, X.; Fang, Y.; Brockett, C.; Galley, M.; Gao, J.; Dolan, B. Joint retrieval and generation training for grounded text generation. arXiv 2021 , arXiv:2105.06597. [ Google Scholar ] [ CrossRef ]
• Pawar, C.S.; Makwana, A. Comparison of BERT-Base and GPT-3 for Marathi Text Classification. In Futuristic Trends in Networks and Computing Technologies: Select Proceedings of Fourth International Conference on FTNCT 2021 ; Springer: Singapore, 2022; pp. 563–574. [ Google Scholar ]
• Bhaskar, A.; Fabbri, A.R.; Durrett, G. Zero-Shot Opinion Summarization with GPT-3. arXiv 2022 , arXiv:2211.15914. [ Google Scholar ] [ CrossRef ]
• Liu, J.; Shen, D.; Zhang, Y.; Dolan, B.; Carin, L.; Chen, W. What Makes Good In-Context Examples for GPT-3? arXiv 2021 , arXiv:2101.06804. [ Google Scholar ] [ CrossRef ]
• Balkus, S.; Yan, D. Improving Short Text Classification With Augmented Data Using GPT-3. arXiv 2022 , arXiv:2205.10981. [ Google Scholar ] [ CrossRef ]
• Madotto, A.; Liu, Z.; Lin, Z.; Fung, P. Language models as few-shot learner for task-oriented dialogue systems. arXiv 2020 , arXiv:2008.06239. [ Google Scholar ] [ CrossRef ]
• Li, X.; Zhang, H.; Zhou, X.H. Chinese clinical named entity recognition with variant neural structures based on BERT methods. J. Biomed. Inform. 2020 , 107 , 103422. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Xu, J.H.; Shinden, K.; Kato, M.P. Table Caption Generation in Scholarly Documents Leveraging Pre-trained Language Models. In Proceedings of the 2021 IEEE 10th Global Conference on Consumer Electronics (GCCE), Kyoto, Japan, 12–15 October 2021. [ Google Scholar ]
• Gasparetto, A.; Marcuzzo, M.; Zangari, A.; Albarelli, A. A Survey on Text Classification Algorithms: From Text to Predictions. Information 2022 , 13 , 83. [ Google Scholar ] [ CrossRef ]
• Chatterjee, J.; Dethlefs, N. This new conversational AI model can be your friend, philosopher, and guide... and even your worst enemy. Patterns 2023 , 4 , 100676. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Perlman, A.M. The Implications of ChatGPT for Legal Services and Society. Available online: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4294197 (accessed on 1 January 2020).
• King, M.R.; chatGPT. A Conversation on Artificial Intelligence, Chatbots, and Plagiarism in Higher Education. Cell. Mol. Bioeng. 2023 , 16 , 1–2. [ Google Scholar ] [ CrossRef ]
• Alshater, M.M. Exploring the Role of Artificial Intelligence in Enhancing Academic Performance: A Case Study of ChatGPT. Available online: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4312358 (accessed on 15 January 2023).
• Mann, D.L. Artificial Intelligence Discusses the Role of Artificial Intelligence in Translational Medicine. JACC Basic Transl. Sci. 2023 , 8 , 221–223. [ Google Scholar ] [ CrossRef ]
• Qadir, J. Engineering Education in the Era of ChatGPT: Promise and Pitfalls of Generative AI for Education. 2022. Available online: https://www.techrxiv.org/articles/preprint/Engineering_Education_in_the_Era_of_ChatGPT_Promise_and_Pitfalls_of_Generative_AI_for_Education/21789434/1 (accessed on 28 January 2023.).
• King, M.R. The future of AI in medicine: A perspective from a Chatbot. Ann. Biomed. Eng. 2022 , 51 , 291–295. [ Google Scholar ] [ CrossRef ]
• Guo, B.; Zhang, X.; Wang, Z.; Jiang, M.; Nie, J.; Ding, Y.; Yue, J.; Wu, Y. How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection. arXiv 2023 , arXiv:2301.07597. [ Google Scholar ] [ CrossRef ]
• McKee, F.; Noever, D. Chatbots in a Botnet World. arXiv 2022 , arXiv:2212.11126. [ Google Scholar ] [ CrossRef ]
• Mijwil, M.; Aljanabi, M. Towards Artificial Intelligence-Based Cybersecurity: The Practices and ChatGPT Generated Ways to Combat Cybercrime. Iraqi J. Comput. Sci. Math. 2023 , 4 , 65–70. [ Google Scholar ]
• Brown, T.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J.D.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; et al. Language models are few-shot learners. In Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, BC, Canada, 6–12 December 2020; Volume 33, pp. 1877–1901. [ Google Scholar ]
• Khandelwal, U.; Levy, O.; Jurafsky, D.; Zettlemoyer, L.; Lewis, M. Generalization through memorization: Nearest neighbor language models. arXiv 2019 , arXiv:1911.00172. [ Google Scholar ] [ CrossRef ]
• Winston, P.H. Artificial Intelligence ; Addison-Wesley Longman Publishing Co., Inc.: Boston, MA, USA, 1984. [ Google Scholar ]
• Zheng, Z.; Xie, S.; Dai, H.N.; Chen, X.; Wang, H. Blockchain challenges and opportunities: A survey. Int. J. Web Grid Serv. 2018 , 14 , 352–375. [ Google Scholar ] [ CrossRef ]
• Tulkunovna, M.D.; Karimboyevich, S.E. The role of artificial intelligence in education. Sci. Innov. 2022 , 1 , 39–45. [ Google Scholar ]
• bin Mohamed, M.Z.; Hidayat, R.; binti Suhaizi, N.N.; bin Mahmud, M.K.H.; binti Baharuddin, S.N. Artificial intelligence in mathematics education: A systematic literature review. Int. Electron. J. Math. Educ. 2022 , 17 , em0694. [ Google Scholar ]
• Litman, D. Natural language processing for enhancing teaching and learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA, 12–17 February 2016. [ Google Scholar ] [ CrossRef ]
• Badnjević, A.; Avdihodžić, H.; Gurbeta Pokvić, L. Artificial intelligence in medical devices: Past, present and future. Psychiatr. Danub. 2021 , 33 , 101–106. [ Google Scholar ] [ CrossRef ]
• Masters, K. Artificial intelligence in medical education. Med. Teach. 2019 , 41 , 976–980. [ Google Scholar ] [ CrossRef ]
• Ziegler, D.M.; Stiennon, N.; Wu, J.; Brown, T.B.; Radford, A.; Amodei, D.; Christiano, P.; Irving, G. Fine-tuning language models from human preferences. arXiv 2019 , arXiv:1909.08593. [ Google Scholar ] [ CrossRef ]
• Chintagunta, B.; Katariya, N.; Amatriain, X.; Kannan, A. Medically aware gpt-3 as a data generator for medical dialogue summarization. In Proceedings of the Machine Learning for Healthcare Conference, PMLR, Virtual Event, 18–24 July 2021; pp. 354–372. [ Google Scholar ]
• Klein, T.; Nabi, M. Learning to answer by learning to ask: Getting the best of gpt-2 and bert worlds. arXiv 2019 , arXiv:1911.02365. [ Google Scholar ] [ CrossRef ]
• Puri, R.; Spring, R.; Patwary, M.; Shoeybi, M.; Catanzaro, B. Training question answering models from synthetic data. arXiv 2020 , arXiv:2002.09599. [ Google Scholar ] [ CrossRef ]
• Muehlematter, U.J.; Daniore, P.; Vokinger, K.N. Approval of artificial intelligence and machine learning-based medical devices in the USA and Europe (2015–20): A comparative analysis. Lancet Digit. Health 2021 , 3 , e195–e203. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Fatima, N.; Imran, A.S.; Kastrati, Z.; Daudpota, S.M.; Soomro, A.; Shaikh, S. A Systematic Literature Review on Text Generation Using Deep Neural Network Models. IEEE Access 2022 , 10 , 53490–53503. [ Google Scholar ] [ CrossRef ]
• Raffel, C.; Shazeer, N.; Roberts, A.; Lee, K.; Narang, S.; Matena, M.; Zhou, Y.; Li, W.; Liu, P.J. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 2020 , 21 , 1–67. [ Google Scholar ]
• Dodge, J.; Sap, M.; Marasović, A.; Agnew, W.; Ilharco, G.; Groeneveld, D.; Mitchell, M.; Gardner, M. Documenting large webtext corpora: A case study on the colossal clean crawled corpus. arXiv 2021 , arXiv:2104.08758. [ Google Scholar ] [ CrossRef ]
• Radford, A.; Wu, J.; Child, R.; Luan, D.; Amodei, D.; Sutskever, I. Language models are unsupervised multitask learners. OpenAI Blog 2019 , 1 , 9. [ Google Scholar ]
• Bandy, J.; Vincent, N. Addressing “documentation deb” in machine learning research: A retrospective datasheet for bookcorpus. arXiv 2021 , arXiv:2105.05241. [ Google Scholar ] [ CrossRef ]
• Antaki, F.; Touma, S.; Milad, D.; El-Khoury, J.; Duval, R. Evaluating the Performance of ChatGPT in Ophthalmology: An Analysis of its Successes and Shortcomings. Ophthalmol. Sci. 2023 , 3 , 100324. [ Google Scholar ] [ CrossRef ]
• Kung, T.H.; Cheatham, M.; Medinilla, A.; ChatGPT; Sillos, C.; De Leon, L.; Elepano, C.; Madriaga, M.; Aggabao, R.; Diaz-Candido, G.; et al. Performance of ChatGPT on USMLE: Potential for AI-Assisted Medical Education Using Large Language Models. PLoS Digit Health 2022 , 2 , e0000198. [ Google Scholar ] [ CrossRef ]
• Sobania, D.; Briesch, M.; Hanna, C.; Petke, J. An Analysis of the Automatic Bug Fixing Performance of ChatGPT. arXiv 2023 , arXiv:2301.08653. [ Google Scholar ] [ CrossRef ]
• Staff, D. ChatGPT Raises Cybersecurity and A.I. Concerns. 2023. Available online: https://www.dice.com/career-advice/chatgpt-raises-cybersecurity-and-a.i.-concerns (accessed on 8 July 2023).
• SharkStriker. Top 4 Most Dangerous Cybersecurity Risks Associated with ChatGPT. 2023. Available online: https://sharkstriker.com/blog/chatgpt-cybersecurity-threat/ (accessed on 8 July 2023).
• Staff, T. Over 100,000 ChatGPT Accounts Stolen and Sold on Dark Web. 2023. Available online: https://www.techradar.com/pro/over-100000-chatgpt-accounts-stolen-and-sold-on-dark-web (accessed on 8 July 2023).
• Lin, X.; Bertasius, G.; Wang, J.; Chang, S.F.; Parikh, D.; Torresani, L. Vx2text: End-to-end learning of video-based text generation from multimodal inputs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20–25 June 2021; pp. 7005–7015. [ Google Scholar ]
• You, Q.; Jin, H.; Wang, Z.; Fang, C.; Luo, J. Image captioning with semantic attention. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 4651–4659. [ Google Scholar ]
• Zhang, S.; Dinan, E.; Urbanek, J.; Szlam, A.; Kiela, D.; Weston, J. Personalizing dialogue agents: I have a dog, do you have pets too? arXiv 2018 , arXiv:1801.07243. [ Google Scholar ] [ CrossRef ]
• Zhang, B.; Xu, X.; Li, X.; Ye, Y.; Chen, X.; Wang, Z. A memory network based end-to-end personalized task-oriented dialogue generation. Knowl.-Based Syst. 2020 , 207 , 106398. [ Google Scholar ] [ CrossRef ]
• Danilevsky, M.; Qian, K.; Aharonov, R.; Katsis, Y.; Kawas, B.; Sen, P. A survey of the state of explainable AI for natural language processing. arXiv 2020 , arXiv:2010.00711. [ Google Scholar ] [ CrossRef ]
• Sennrich, R.; Zhang, B. Revisiting low-resource neural machine translation: A case study. arXiv 2019 , arXiv:1905.11901. [ Google Scholar ] [ CrossRef ]
• Vrbančič, G.; Podgorelec, V. Transfer learning with adaptive fine-tuning. IEEE Access 2020 , 8 , 196197–196211. [ Google Scholar ] [ CrossRef ]
• Zhu, M.; Pan, P.; Chen, W.; Yang, Y. Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 5802–5810. [ Google Scholar ]

Click here to enlarge figure

Share and Cite

Alawida, M.; Mejri, S.; Mehmood, A.; Chikhaoui, B.; Isaac Abiodun, O. A Comprehensive Study of ChatGPT: Advancements, Limitations, and Ethical Considerations in Natural Language Processing and Cybersecurity. Information 2023 , 14 , 462. https://doi.org/10.3390/info14080462

Alawida M, Mejri S, Mehmood A, Chikhaoui B, Isaac Abiodun O. A Comprehensive Study of ChatGPT: Advancements, Limitations, and Ethical Considerations in Natural Language Processing and Cybersecurity. Information . 2023; 14(8):462. https://doi.org/10.3390/info14080462

Alawida, Moatsum, Sami Mejri, Abid Mehmood, Belkacem Chikhaoui, and Oludare Isaac Abiodun. 2023. "A Comprehensive Study of ChatGPT: Advancements, Limitations, and Ethical Considerations in Natural Language Processing and Cybersecurity" Information 14, no. 8: 462. https://doi.org/10.3390/info14080462

Article Metrics

Article access statistics, further information, mdpi initiatives, follow mdpi.

Subscribe to receive issue release notifications and newsletters from MDPI journals

Advertisement

A systematic literature review of empirical research on ChatGPT in education

• Open access
• Published: 26 May 2024
• Volume 3 , article number  60 , ( 2024 )

Cite this article

You have full access to this open access article

• Yazid Albadarin   ORCID: orcid.org/0009-0005-8068-8902 1 ,
• Mohammed Saqr 1 ,
• Nicolas Pope 1 &
• Markku Tukiainen 1  

4123 Accesses

Explore all metrics

Over the last four decades, studies have investigated the incorporation of Artificial Intelligence (AI) into education. A recent prominent AI-powered technology that has impacted the education sector is ChatGPT. This article provides a systematic review of 14 empirical studies incorporating ChatGPT into various educational settings, published in 2022 and before the 10th of April 2023—the date of conducting the search process. It carefully followed the essential steps outlined in the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) guidelines, as well as Okoli’s (Okoli in Commun Assoc Inf Syst, 2015) steps for conducting a rigorous and transparent systematic review. In this review, we aimed to explore how students and teachers have utilized ChatGPT in various educational settings, as well as the primary findings of those studies. By employing Creswell’s (Creswell in Educational research: planning, conducting, and evaluating quantitative and qualitative research [Ebook], Pearson Education, London, 2015) coding techniques for data extraction and interpretation, we sought to gain insight into their initial attempts at ChatGPT incorporation into education. This approach also enabled us to extract insights and considerations that can facilitate its effective and responsible use in future educational contexts. The results of this review show that learners have utilized ChatGPT as a virtual intelligent assistant, where it offered instant feedback, on-demand answers, and explanations of complex topics. Additionally, learners have used it to enhance their writing and language skills by generating ideas, composing essays, summarizing, translating, paraphrasing texts, or checking grammar. Moreover, learners turned to it as an aiding tool to facilitate their directed and personalized learning by assisting in understanding concepts and homework, providing structured learning plans, and clarifying assignments and tasks. However, the results of specific studies (n = 3, 21.4%) show that overuse of ChatGPT may negatively impact innovative capacities and collaborative learning competencies among learners. Educators, on the other hand, have utilized ChatGPT to create lesson plans, generate quizzes, and provide additional resources, which helped them enhance their productivity and efficiency and promote different teaching methodologies. Despite these benefits, the majority of the reviewed studies recommend the importance of conducting structured training, support, and clear guidelines for both learners and educators to mitigate the drawbacks. This includes developing critical evaluation skills to assess the accuracy and relevance of information provided by ChatGPT, as well as strategies for integrating human interaction and collaboration into learning activities that involve AI tools. Furthermore, they also recommend ongoing research and proactive dialogue with policymakers, stakeholders, and educational practitioners to refine and enhance the use of AI in learning environments. This review could serve as an insightful resource for practitioners who seek to integrate ChatGPT into education and stimulate further research in the field.

Similar content being viewed by others

Empowering learners with ChatGPT: insights from a systematic literature exploration

Incorporating AI in foreign language education: An investigation into ChatGPT’s effect on foreign language learners

Large language models in education: A focus on the complementary relationship between human teachers and ChatGPT

Explore related subjects.

• Artificial Intelligence

Avoid common mistakes on your manuscript.

1 Introduction

Educational technology, a rapidly evolving field, plays a crucial role in reshaping the landscape of teaching and learning [ 82 ]. One of the most transformative technological innovations of our era that has influenced the field of education is Artificial Intelligence (AI) [ 50 ]. Over the last four decades, AI in education (AIEd) has gained remarkable attention for its potential to make significant advancements in learning, instructional methods, and administrative tasks within educational settings [ 11 ]. In particular, a large language model (LLM), a type of AI algorithm that applies artificial neural networks (ANNs) and uses massively large data sets to understand, summarize, generate, and predict new content that is almost difficult to differentiate from human creations [ 79 ], has opened up novel possibilities for enhancing various aspects of education, from content creation to personalized instruction [ 35 ]. Chatbots that leverage the capabilities of LLMs to understand and generate human-like responses have also presented the capacity to enhance student learning and educational outcomes by engaging students, offering timely support, and fostering interactive learning experiences [ 46 ].

The ongoing and remarkable technological advancements in chatbots have made their use more convenient, increasingly natural and effortless, and have expanded their potential for deployment across various domains [ 70 ]. One prominent example of chatbot applications is the Chat Generative Pre-Trained Transformer, known as ChatGPT, which was introduced by OpenAI, a leading AI research lab, on November 30th, 2022. ChatGPT employs a variety of deep learning techniques to generate human-like text, with a particular focus on recurrent neural networks (RNNs). Long short-term memory (LSTM) allows it to grasp the context of the text being processed and retain information from previous inputs. Also, the transformer architecture, a neural network architecture based on the self-attention mechanism, allows it to analyze specific parts of the input, thereby enabling it to produce more natural-sounding and coherent output. Additionally, the unsupervised generative pre-training and the fine-tuning methods allow ChatGPT to generate more relevant and accurate text for specific tasks [ 31 , 62 ]. Furthermore, reinforcement learning from human feedback (RLHF), a machine learning approach that combines reinforcement learning techniques with human-provided feedback, has helped improve ChatGPT’s model by accelerating the learning process and making it significantly more efficient.

This cutting-edge natural language processing (NLP) tool is widely recognized as one of today's most advanced LLMs-based chatbots [ 70 ], allowing users to ask questions and receive detailed, coherent, systematic, personalized, convincing, and informative human-like responses [ 55 ], even within complex and ambiguous contexts [ 63 , 77 ]. ChatGPT is considered the fastest-growing technology in history: in just three months following its public launch, it amassed an estimated 120 million monthly active users [ 16 ] with an estimated 13 million daily queries [ 49 ], surpassing all other applications [ 64 ]. This remarkable growth can be attributed to the unique features and user-friendly interface that ChatGPT offers. Its intuitive design allows users to interact seamlessly with the technology, making it accessible to a diverse range of individuals, regardless of their technical expertise [ 78 ]. Additionally, its exceptional performance results from a combination of advanced algorithms, continuous enhancements, and extensive training on a diverse dataset that includes various text sources such as books, articles, websites, and online forums [ 63 ], have contributed to a more engaging and satisfying user experience [ 62 ]. These factors collectively explain its remarkable global growth and set it apart from predecessors like Bard, Bing Chat, ERNIE, and others.

In this context, several studies have explored the technological advancements of chatbots. One noteworthy recent research effort, conducted by Schöbel et al. [ 70 ], stands out for its comprehensive analysis of more than 5,000 studies on communication agents. This study offered a comprehensive overview of the historical progression and future prospects of communication agents, including ChatGPT. Moreover, other studies have focused on making comparisons, particularly between ChatGPT and alternative chatbots like Bard, Bing Chat, ERNIE, LaMDA, BlenderBot, and various others. For example, O’Leary [ 53 ] compared two chatbots, LaMDA and BlenderBot, with ChatGPT and revealed that ChatGPT outperformed both. This superiority arises from ChatGPT’s capacity to handle a wider range of questions and generate slightly varied perspectives within specific contexts. Similarly, ChatGPT exhibited an impressive ability to formulate interpretable responses that were easily understood when compared with Google's feature snippet [ 34 ]. Additionally, ChatGPT was compared to other LLMs-based chatbots, including Bard and BERT, as well as ERNIE. The findings indicated that ChatGPT exhibited strong performance in the given tasks, often outperforming the other models [ 59 ].

Furthermore, in the education context, a comprehensive study systematically compared a range of the most promising chatbots, including Bard, Bing Chat, ChatGPT, and Ernie across a multidisciplinary test that required higher-order thinking. The study revealed that ChatGPT achieved the highest score, surpassing Bing Chat and Bard [ 64 ]. Similarly, a comparative analysis was conducted to compare ChatGPT with Bard in answering a set of 30 mathematical questions and logic problems, grouped into two question sets. Set (A) is unavailable online, while Set (B) is available online. The results revealed ChatGPT's superiority in Set (A) over Bard. Nevertheless, Bard's advantage emerged in Set (B) due to its capacity to access the internet directly and retrieve answers, a capability that ChatGPT does not possess [ 57 ]. However, through these varied assessments, ChatGPT consistently highlights its exceptional prowess compared to various alternatives in the ever-evolving chatbot technology.

The widespread adoption of chatbots, especially ChatGPT, by millions of students and educators, has sparked extensive discussions regarding its incorporation into the education sector [ 64 ]. Accordingly, many scholars have contributed to the discourse, expressing both optimism and pessimism regarding the incorporation of ChatGPT into education. For example, ChatGPT has been highlighted for its capabilities in enriching the learning and teaching experience through its ability to support different learning approaches, including adaptive learning, personalized learning, and self-directed learning [ 58 , 60 , 91 ]), deliver summative and formative feedback to students and provide real-time responses to questions, increase the accessibility of information [ 22 , 40 , 43 ], foster students’ performance, engagement and motivation [ 14 , 44 , 58 ], and enhance teaching practices [ 17 , 18 , 64 , 74 ].

On the other hand, concerns have been also raised regarding its potential negative effects on learning and teaching. These include the dissemination of false information and references [ 12 , 23 , 61 , 85 ], biased reinforcement [ 47 , 50 ], compromised academic integrity [ 18 , 40 , 66 , 74 ], and the potential decline in students' skills [ 43 , 61 , 64 , 74 ]. As a result, ChatGPT has been banned in multiple countries, including Russia, China, Venezuela, Belarus, and Iran, as well as in various educational institutions in India, Italy, Western Australia, France, and the United States [ 52 , 90 ].

Clearly, the advent of chatbots, especially ChatGPT, has provoked significant controversy due to their potential impact on learning and teaching. This indicates the necessity for further exploration to gain a deeper understanding of this technology and carefully evaluate its potential benefits, limitations, challenges, and threats to education [ 79 ]. Therefore, conducting a systematic literature review will provide valuable insights into the potential prospects and obstacles linked to its incorporation into education. This systematic literature review will primarily focus on ChatGPT, driven by the aforementioned key factors outlined above.

However, the existing literature lacks a systematic literature review of empirical studies. Thus, this systematic literature review aims to address this gap by synthesizing the existing empirical studies conducted on chatbots, particularly ChatGPT, in the field of education, highlighting how ChatGPT has been utilized in educational settings, and identifying any existing gaps. This review may be particularly useful for researchers in the field and educators who are contemplating the integration of ChatGPT or any chatbot into education. The following research questions will guide this study:

What are students' and teachers' initial attempts at utilizing ChatGPT in education?

What are the main findings derived from empirical studies that have incorporated ChatGPT into learning and teaching?

2 Methodology

To conduct this study, the authors followed the essential steps of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) and Okoli’s [ 54 ] steps for conducting a systematic review. These included identifying the study’s purpose, drafting a protocol, applying a practical screening process, searching the literature, extracting relevant data, evaluating the quality of the included studies, synthesizing the studies, and ultimately writing the review. The subsequent section provides an extensive explanation of how these steps were carried out in this study.

2.1 Identify the purpose

Given the widespread adoption of ChatGPT by students and teachers for various educational purposes, often without a thorough understanding of responsible and effective use or a clear recognition of its potential impact on learning and teaching, the authors recognized the need for further exploration of ChatGPT's impact on education in this early stage. Therefore, they have chosen to conduct a systematic literature review of existing empirical studies that incorporate ChatGPT into educational settings. Despite the limited number of empirical studies due to the novelty of the topic, their goal is to gain a deeper understanding of this technology and proactively evaluate its potential benefits, limitations, challenges, and threats to education. This effort could help to understand initial reactions and attempts at incorporating ChatGPT into education and bring out insights and considerations that can inform the future development of education.

2.2 Draft the protocol

The next step is formulating the protocol. This protocol serves to outline the study process in a rigorous and transparent manner, mitigating researcher bias in study selection and data extraction [ 88 ]. The protocol will include the following steps: generating the research question, predefining a literature search strategy, identifying search locations, establishing selection criteria, assessing the studies, developing a data extraction strategy, and creating a timeline.

2.3 Apply practical screen

The screening step aims to accurately filter the articles resulting from the searching step and select the empirical studies that have incorporated ChatGPT into educational contexts, which will guide us in answering the research questions and achieving the objectives of this study. To ensure the rigorous execution of this step, our inclusion and exclusion criteria were determined based on the authors' experience and informed by previous successful systematic reviews [ 21 ]. Table 1 summarizes the inclusion and exclusion criteria for study selection.

2.4 Literature search

We conducted a thorough literature search to identify articles that explored, examined, and addressed the use of ChatGPT in Educational contexts. We utilized two research databases: Dimensions.ai, which provides access to a large number of research publications, and lens.org, which offers access to over 300 million articles, patents, and other research outputs from diverse sources. Additionally, we included three databases, Scopus, Web of Knowledge, and ERIC, which contain relevant research on the topic that addresses our research questions. To browse and identify relevant articles, we used the following search formula: ("ChatGPT" AND "Education"), which included the Boolean operator "AND" to get more specific results. The subject area in the Scopus and ERIC databases were narrowed to "ChatGPT" and "Education" keywords, and in the WoS database was limited to the "Education" category. The search was conducted between the 3rd and 10th of April 2023, which resulted in 276 articles from all selected databases (111 articles from Dimensions.ai, 65 from Scopus, 28 from Web of Science, 14 from ERIC, and 58 from Lens.org). These articles were imported into the Rayyan web-based system for analysis. The duplicates were identified automatically by the system. Subsequently, the first author manually reviewed the duplicated articles ensured that they had the same content, and then removed them, leaving us with 135 unique articles. Afterward, the titles, abstracts, and keywords of the first 40 manuscripts were scanned and reviewed by the first author and were discussed with the second and third authors to resolve any disagreements. Subsequently, the first author proceeded with the filtering process for all articles and carefully applied the inclusion and exclusion criteria as presented in Table  1 . Articles that met any one of the exclusion criteria were eliminated, resulting in 26 articles. Afterward, the authors met to carefully scan and discuss them. The authors agreed to eliminate any empirical studies solely focused on checking ChatGPT capabilities, as these studies do not guide us in addressing the research questions and achieving the study's objectives. This resulted in 14 articles eligible for analysis.

2.5 Quality appraisal

The examination and evaluation of the quality of the extracted articles is a vital step [ 9 ]. Therefore, the extracted articles were carefully evaluated for quality using Fink’s [ 24 ] standards, which emphasize the necessity for detailed descriptions of methodology, results, conclusions, strengths, and limitations. The process began with a thorough assessment of each study's design, data collection, and analysis methods to ensure their appropriateness and comprehensive execution. The clarity, consistency, and logical progression from data to results and conclusions were also critically examined. Potential biases and recognized limitations within the studies were also scrutinized. Ultimately, two articles were excluded for failing to meet Fink’s criteria, particularly in providing sufficient detail on methodology, results, conclusions, strengths, or limitations. The review process is illustrated in Fig.  1 .

The study selection process

2.6 Data extraction

The next step is data extraction, the process of capturing the key information and categories from the included studies. To improve efficiency, reduce variation among authors, and minimize errors in data analysis, the coding categories were constructed using Creswell's [ 15 ] coding techniques for data extraction and interpretation. The coding process involves three sequential steps. The initial stage encompasses open coding , where the researcher examines the data, generates codes to describe and categorize it, and gains a deeper understanding without preconceived ideas. Following open coding is axial coding , where the interrelationships between codes from open coding are analyzed to establish more comprehensive categories or themes. The process concludes with selective coding , refining and integrating categories or themes to identify core concepts emerging from the data. The first coder performed the coding process, then engaged in discussions with the second and third authors to finalize the coding categories for the first five articles. The first coder then proceeded to code all studies and engaged again in discussions with the other authors to ensure the finalization of the coding process. After a comprehensive analysis and capturing of the key information from the included studies, the data extraction and interpretation process yielded several themes. These themes have been categorized and are presented in Table  2 . It is important to note that open coding results were removed from Table  2 for aesthetic reasons, as it included many generic aspects, such as words, short phrases, or sentences mentioned in the studies.

2.7 Synthesize studies

In this stage, we will gather, discuss, and analyze the key findings that emerged from the selected studies. The synthesis stage is considered a transition from an author-centric to a concept-centric focus, enabling us to map all the provided information to achieve the most effective evaluation of the data [ 87 ]. Initially, the authors extracted data that included general information about the selected studies, including the author(s)' names, study titles, years of publication, educational levels, research methodologies, sample sizes, participants, main aims or objectives, raw data sources, and analysis methods. Following that, all key information and significant results from the selected studies were compiled using Creswell’s [ 15 ] coding techniques for data extraction and interpretation to identify core concepts and themes emerging from the data, focusing on those that directly contributed to our research questions and objectives, such as the initial utilization of ChatGPT in learning and teaching, learners' and educators' familiarity with ChatGPT, and the main findings of each study. Finally, the data related to each selected study were extracted into an Excel spreadsheet for data processing. The Excel spreadsheet was reviewed by the authors, including a series of discussions to ensure the finalization of this process and prepare it for further analysis. Afterward, the final result being analyzed and presented in various types of charts and graphs. Table 4 presents the extracted data from the selected studies, with each study labeled with a capital 'S' followed by a number.

This section consists of two main parts. The first part provides a descriptive analysis of the data compiled from the reviewed studies. The second part presents the answers to the research questions and the main findings of these studies.

3.1 Part 1: descriptive analysis

This section will provide a descriptive analysis of the reviewed studies, including educational levels and fields, participants distribution, country contribution, research methodologies, study sample size, study population, publication year, list of journals, familiarity with ChatGPT, source of data, and the main aims and objectives of the studies. Table 4 presents a comprehensive overview of the extracted data from the selected studies.

3.1.1 The number of the reviewed studies and publication years

The total number of the reviewed studies was 14. All studies were empirical studies and published in different journals focusing on Education and Technology. One study was published in 2022 [S1], while the remaining were published in 2023 [S2]-[S14]. Table 3 illustrates the year of publication, the names of the journals, and the number of reviewed studies published in each journal for the studies reviewed.

3.1.2 Educational levels and fields

The majority of the reviewed studies, 11 studies, were conducted in higher education institutions [S1]-[S10] and [S13]. Two studies did not specify the educational level of the population [S12] and [S14], while one study focused on elementary education [S11]. However, the reviewed studies covered various fields of education. Three studies focused on Arts and Humanities Education [S8], [S11], and [S14], specifically English Education. Two studies focused on Engineering Education, with one in Computer Engineering [S2] and the other in Construction Education [S3]. Two studies focused on Mathematics Education [S5] and [S12]. One study focused on Social Science Education [S13]. One study focused on Early Education [S4]. One study focused on Journalism Education [S9]. Finally, three studies did not specify the field of education [S1], [S6], and [S7]. Figure  2 represents the educational levels in the reviewed studies, while Fig.  3 represents the context of the reviewed studies.

Educational levels in the reviewed studies

Context of the reviewed studies

3.1.3 Participants distribution and countries contribution

The reviewed studies have been conducted across different geographic regions, providing a diverse representation of the studies. The majority of the studies, 10 in total, [S1]-[S3], [S5]-[S9], [S11], and [S14], primarily focused on participants from single countries such as Pakistan, the United Arab Emirates, China, Indonesia, Poland, Saudi Arabia, South Korea, Spain, Tajikistan, and the United States. In contrast, four studies, [S4], [S10], [S12], and [S13], involved participants from multiple countries, including China and the United States [S4], China, the United Kingdom, and the United States [S10], the United Arab Emirates, Oman, Saudi Arabia, and Jordan [S12], Turkey, Sweden, Canada, and Australia [ 13 ]. Figures  4 and 5 illustrate the distribution of participants, whether from single or multiple countries, and the contribution of each country in the reviewed studies, respectively.

The reviewed studies conducted in single or multiple countries

The Contribution of each country in the studies

3.1.4 Study population and sample size

Four study populations were included: university students, university teachers, university teachers and students, and elementary school teachers. Six studies involved university students [S2], [S3], [S5] and [S6]-[S8]. Three studies focused on university teachers [S1], [S4], and [S6], while one study specifically targeted elementary school teachers [S11]. Additionally, four studies included both university teachers and students [S10] and [ 12 , 13 , 14 ], and among them, study [S13] specifically included postgraduate students. In terms of the sample size of the reviewed studies, nine studies included a small sample size of less than 50 participants [S1], [S3], [S6], [S8], and [S10]-[S13]. Three studies had 50–100 participants [S2], [S9], and [S14]. Only one study had more than 100 participants [S7]. It is worth mentioning that study [S4] adopted a mixed methods approach, including 10 participants for qualitative analysis and 110 participants for quantitative analysis.

3.1.5 Participants’ familiarity with using ChatGPT

The reviewed studies recruited a diverse range of participants with varying levels of familiarity with ChatGPT. Five studies [S2], [S4], [S6], [S8], and [S12] involved participants already familiar with ChatGPT, while eight studies [S1], [S3], [S5], [S7], [S9], [S10], [S13] and [S14] included individuals with differing levels of familiarity. Notably, one study [S11] had participants who were entirely unfamiliar with ChatGPT. It is important to note that four studies [S3], [S5], [S9], and [S11] provided training or guidance to their participants before conducting their studies, while ten studies [S1], [S2], [S4], [S6]-[S8], [S10], and [S12]-[S14] did not provide training due to the participants' existing familiarity with ChatGPT.

3.1.6 Research methodology approaches and source(S) of data

The reviewed studies adopted various research methodology approaches. Seven studies adopted qualitative research methodology [S1], [S4], [S6], [S8], [S10], [S11], and [S12], while three studies adopted quantitative research methodology [S3], [S7], and [S14], and four studies employed mixed-methods, which involved a combination of both the strengths of qualitative and quantitative methods [S2], [S5], [S9], and [S13].

In terms of the source(s) of data, the reviewed studies obtained their data from various sources, such as interviews, questionnaires, and pre-and post-tests. Six studies relied on interviews as their primary source of data collection [S1], [S4], [S6], [S10], [S11], and [S12], four studies relied on questionnaires [S2], [S7], [S13], and [S14], two studies combined the use of pre-and post-tests and questionnaires for data collection [S3] and [S9], while two studies combined the use of questionnaires and interviews to obtain the data [S5] and [S8]. It is important to note that six of the reviewed studies were quasi-experimental [S3], [S5], [S8], [S9], [S12], and [S14], while the remaining ones were experimental studies [S1], [S2], [S4], [S6], [S7], [S10], [S11], and [S13]. Figures  6 and 7 illustrate the research methodologies and the source (s) of data used in the reviewed studies, respectively.

Research methodologies in the reviewed studies

Source of data in the reviewed studies

3.1.7 The aim and objectives of the studies

The reviewed studies encompassed a diverse set of aims, with several of them incorporating multiple primary objectives. Six studies [S3], [S6], [S7], [S8], [S11], and [S12] examined the integration of ChatGPT in educational contexts, and four studies [S4], [S5], [S13], and [S14] investigated the various implications of its use in education, while three studies [S2], [S9], and [S10] aimed to explore both its integration and implications in education. Additionally, seven studies explicitly explored attitudes and perceptions of students [S2] and [S3], educators [S1] and [S6], or both [S10], [S12], and [S13] regarding the utilization of ChatGPT in educational settings.

3.2 Part 2: research questions and main findings of the reviewed studies

This part will present the answers to the research questions and the main findings of the reviewed studies, classified into two main categories (learning and teaching) according to AI Education classification by [ 36 ]. Figure  8 summarizes the main findings of the reviewed studies in a visually informative diagram. Table 4 provides a detailed list of the key information extracted from the selected studies that led to generating these themes.

The main findings in the reviewed studies

4 Students' initial attempts at utilizing ChatGPT in learning and main findings from students' perspective

4.1 virtual intelligent assistant.

Nine studies demonstrated that ChatGPT has been utilized by students as an intelligent assistant to enhance and support their learning. Students employed it for various purposes, such as answering on-demand questions [S2]-[S5], [S8], [S10], and [S12], providing valuable information and learning resources [S2]-[S5], [S6], and [S8], as well as receiving immediate feedback [S2], [S4], [S9], [S10], and [S12]. In this regard, students generally were confident in the accuracy of ChatGPT's responses, considering them relevant, reliable, and detailed [S3], [S4], [S5], and [S8]. However, some students indicated the need for improvement, as they found that answers are not always accurate [S2], and that misleading information may have been provided or that it may not always align with their expectations [S6] and [S10]. It was also observed by the students that the accuracy of ChatGPT is dependent on several factors, including the quality and specificity of the user's input, the complexity of the question or topic, and the scope and relevance of its training data [S12]. Many students felt that ChatGPT's answers were not always accurate and most of them believed that it requires good background knowledge to work with.

4.2 Writing and language proficiency assistant

Six of the reviewed studies highlighted that ChatGPT has been utilized by students as a valuable assistant tool to improve their academic writing skills and language proficiency. Among these studies, three mainly focused on English education, demonstrating that students showed sufficient mastery in using ChatGPT for generating ideas, summarizing, paraphrasing texts, and completing writing essays [S8], [S11], and [S14]. Furthermore, ChatGPT helped them in writing by making students active investigators rather than passive knowledge recipients and facilitated the development of their writing skills [S11] and [S14]. Similarly, ChatGPT allowed students to generate unique ideas and perspectives, leading to deeper analysis and reflection on their journalism writing [S9]. In terms of language proficiency, ChatGPT allowed participants to translate content into their home languages, making it more accessible and relevant to their context [S4]. It also enabled them to request changes in linguistic tones or flavors [S8]. Moreover, participants used it to check grammar or as a dictionary [S11].

4.3 Valuable resource for learning approaches

Five studies demonstrated that students used ChatGPT as a valuable complementary resource for self-directed learning. It provided learning resources and guidance on diverse educational topics and created a supportive home learning environment [S2] and [S4]. Moreover, it offered step-by-step guidance to grasp concepts at their own pace and enhance their understanding [S5], streamlined task and project completion carried out independently [S7], provided comprehensive and easy-to-understand explanations on various subjects [S10], and assisted in studying geometry operations, thereby empowering them to explore geometry operations at their own pace [S12]. Three studies showed that students used ChatGPT as a valuable learning resource for personalized learning. It delivered age-appropriate conversations and tailored teaching based on a child's interests [S4], acted as a personalized learning assistant, adapted to their needs and pace, which assisted them in understanding mathematical concepts [S12], and enabled personalized learning experiences in social sciences by adapting to students' needs and learning styles [S13]. On the other hand, it is important to note that, according to one study [S5], students suggested that using ChatGPT may negatively affect collaborative learning competencies between students.

4.4 Enhancing students' competencies

Six of the reviewed studies have shown that ChatGPT is a valuable tool for improving a wide range of skills among students. Two studies have provided evidence that ChatGPT led to improvements in students' critical thinking, reasoning skills, and hazard recognition competencies through engaging them in interactive conversations or activities and providing responses related to their disciplines in journalism [S5] and construction education [S9]. Furthermore, two studies focused on mathematical education have shown the positive impact of ChatGPT on students' problem-solving abilities in unraveling problem-solving questions [S12] and enhancing the students' understanding of the problem-solving process [S5]. Lastly, one study indicated that ChatGPT effectively contributed to the enhancement of conversational social skills [S4].

4.5 Supporting students' academic success

Seven of the reviewed studies highlighted that students found ChatGPT to be beneficial for learning as it enhanced learning efficiency and improved the learning experience. It has been observed to improve students' efficiency in computer engineering studies by providing well-structured responses and good explanations [S2]. Additionally, students found it extremely useful for hazard reporting [S3], and it also enhanced their efficiency in solving mathematics problems and capabilities [S5] and [S12]. Furthermore, by finding information, generating ideas, translating texts, and providing alternative questions, ChatGPT aided students in deepening their understanding of various subjects [S6]. It contributed to an increase in students' overall productivity [S7] and improved efficiency in composing written tasks [S8]. Regarding learning experiences, ChatGPT was instrumental in assisting students in identifying hazards that they might have otherwise overlooked [S3]. It also improved students' learning experiences in solving mathematics problems and developing abilities [S5] and [S12]. Moreover, it increased students' successful completion of important tasks in their studies [S7], particularly those involving average difficulty writing tasks [S8]. Additionally, ChatGPT increased the chances of educational success by providing students with baseline knowledge on various topics [S10].

5 Teachers' initial attempts at utilizing ChatGPT in teaching and main findings from teachers' perspective

5.1 valuable resource for teaching.

The reviewed studies showed that teachers have employed ChatGPT to recommend, modify, and generate diverse, creative, organized, and engaging educational contents, teaching materials, and testing resources more rapidly [S4], [S6], [S10] and [S11]. Additionally, teachers experienced increased productivity as ChatGPT facilitated quick and accurate responses to questions, fact-checking, and information searches [S1]. It also proved valuable in constructing new knowledge [S6] and providing timely answers to students' questions in classrooms [S11]. Moreover, ChatGPT enhanced teachers' efficiency by generating new ideas for activities and preplanning activities for their students [S4] and [S6], including interactive language game partners [S11].

5.2 Improving productivity and efficiency

The reviewed studies showed that participants' productivity and work efficiency have been significantly enhanced by using ChatGPT as it enabled them to allocate more time to other tasks and reduce their overall workloads [S6], [S10], [S11], [S13], and [S14]. However, three studies [S1], [S4], and [S11], indicated a negative perception and attitude among teachers toward using ChatGPT. This negativity stemmed from a lack of necessary skills to use it effectively [S1], a limited familiarity with it [S4], and occasional inaccuracies in the content provided by it [S10].

5.3 Catalyzing new teaching methodologies

Five of the reviewed studies highlighted that educators found the necessity of redefining their teaching profession with the assistance of ChatGPT [S11], developing new effective learning strategies [S4], and adapting teaching strategies and methodologies to ensure the development of essential skills for future engineers [S5]. They also emphasized the importance of adopting new educational philosophies and approaches that can evolve with the introduction of ChatGPT into the classroom [S12]. Furthermore, updating curricula to focus on improving human-specific features, such as emotional intelligence, creativity, and philosophical perspectives [S13], was found to be essential.

5.4 Effective utilization of CHATGPT in teaching

According to the reviewed studies, effective utilization of ChatGPT in education requires providing teachers with well-structured training, support, and adequate background on how to use ChatGPT responsibly [S1], [S3], [S11], and [S12]. Establishing clear rules and regulations regarding its usage is essential to ensure it positively impacts the teaching and learning processes, including students' skills [S1], [S4], [S5], [S8], [S9], and [S11]-[S14]. Moreover, conducting further research and engaging in discussions with policymakers and stakeholders is indeed crucial for the successful integration of ChatGPT in education and to maximize the benefits for both educators and students [S1], [S6]-[S10], and [S12]-[S14].

6 Discussion

The purpose of this review is to conduct a systematic review of empirical studies that have explored the utilization of ChatGPT, one of today’s most advanced LLM-based chatbots, in education. The findings of the reviewed studies showed several ways of ChatGPT utilization in different learning and teaching practices as well as it provided insights and considerations that can facilitate its effective and responsible use in future educational contexts. The results of the reviewed studies came from diverse fields of education, which helped us avoid a biased review that is limited to a specific field. Similarly, the reviewed studies have been conducted across different geographic regions. This kind of variety in geographic representation enriched the findings of this review.

In response to RQ1 , "What are students' and teachers' initial attempts at utilizing ChatGPT in education?", the findings from this review provide comprehensive insights. Chatbots, including ChatGPT, play a crucial role in supporting student learning, enhancing their learning experiences, and facilitating diverse learning approaches [ 42 , 43 ]. This review found that this tool, ChatGPT, has been instrumental in enhancing students' learning experiences by serving as a virtual intelligent assistant, providing immediate feedback, on-demand answers, and engaging in educational conversations. Additionally, students have benefited from ChatGPT’s ability to generate ideas, compose essays, and perform tasks like summarizing, translating, paraphrasing texts, or checking grammar, thereby enhancing their writing and language competencies. Furthermore, students have turned to ChatGPT for assistance in understanding concepts and homework, providing structured learning plans, and clarifying assignments and tasks, which fosters a supportive home learning environment, allowing them to take responsibility for their own learning and cultivate the skills and approaches essential for supportive home learning environment [ 26 , 27 , 28 ]. This finding aligns with the study of Saqr et al. [ 68 , 69 ] who highlighted that, when students actively engage in their own learning process, it yields additional advantages, such as heightened motivation, enhanced achievement, and the cultivation of enthusiasm, turning them into advocates for their own learning.

Moreover, students have utilized ChatGPT for tailored teaching and step-by-step guidance on diverse educational topics, streamlining task and project completion, and generating and recommending educational content. This personalization enhances the learning environment, leading to increased academic success. This finding aligns with other recent studies [ 26 , 27 , 28 , 60 , 66 ] which revealed that ChatGPT has the potential to offer personalized learning experiences and support an effective learning process by providing students with customized feedback and explanations tailored to their needs and abilities. Ultimately, fostering students' performance, engagement, and motivation, leading to increase students' academic success [ 14 , 44 , 58 ]. This ultimate outcome is in line with the findings of Saqr et al. [ 68 , 69 ], which emphasized that learning strategies are important catalysts of students' learning, as students who utilize effective learning strategies are more likely to have better academic achievement.

Teachers, too, have capitalized on ChatGPT's capabilities to enhance productivity and efficiency, using it for creating lesson plans, generating quizzes, providing additional resources, generating and preplanning new ideas for activities, and aiding in answering students’ questions. This adoption of technology introduces new opportunities to support teaching and learning practices, enhancing teacher productivity. This finding aligns with those of Day [ 17 ], De Castro [ 18 ], and Su and Yang [ 74 ] as well as with those of Valtonen et al. [ 82 ], who revealed that emerging technological advancements have opened up novel opportunities and means to support teaching and learning practices, and enhance teachers’ productivity.

In response to RQ2 , "What are the main findings derived from empirical studies that have incorporated ChatGPT into learning and teaching?", the findings from this review provide profound insights and raise significant concerns. Starting with the insights, chatbots, including ChatGPT, have demonstrated the potential to reshape and revolutionize education, creating new, novel opportunities for enhancing the learning process and outcomes [ 83 ], facilitating different learning approaches, and offering a range of pedagogical benefits [ 19 , 43 , 72 ]. In this context, this review found that ChatGPT could open avenues for educators to adopt or develop new effective learning and teaching strategies that can evolve with the introduction of ChatGPT into the classroom. Nonetheless, there is an evident lack of research understanding regarding the potential impact of generative machine learning models within diverse educational settings [ 83 ]. This necessitates teachers to attain a high level of proficiency in incorporating chatbots, such as ChatGPT, into their classrooms to create inventive, well-structured, and captivating learning strategies. In the same vein, the review also found that teachers without the requisite skills to utilize ChatGPT realized that it did not contribute positively to their work and could potentially have adverse effects [ 37 ]. This concern could lead to inequity of access to the benefits of chatbots, including ChatGPT, as individuals who lack the necessary expertise may not be able to harness their full potential, resulting in disparities in educational outcomes and opportunities. Therefore, immediate action is needed to address these potential issues. A potential solution is offering training, support, and competency development for teachers to ensure that all of them can leverage chatbots, including ChatGPT, effectively and equitably in their educational practices [ 5 , 28 , 80 ], which could enhance accessibility and inclusivity, and potentially result in innovative outcomes [ 82 , 83 ].

Additionally, chatbots, including ChatGPT, have the potential to significantly impact students' thinking abilities, including retention, reasoning, analysis skills [ 19 , 45 ], and foster innovation and creativity capabilities [ 83 ]. This review found that ChatGPT could contribute to improving a wide range of skills among students. However, it found that frequent use of ChatGPT may result in a decrease in innovative capacities, collaborative skills and cognitive capacities, and students' motivation to attend classes, as well as could lead to reduced higher-order thinking skills among students [ 22 , 29 ]. Therefore, immediate action is needed to carefully examine the long-term impact of chatbots such as ChatGPT, on learning outcomes as well as to explore its incorporation into educational settings as a supportive tool without compromising students' cognitive development and critical thinking abilities. In the same vein, the review also found that it is challenging to draw a consistent conclusion regarding the potential of ChatGPT to aid self-directed learning approach. This finding aligns with the recent study of Baskara [ 8 ]. Therefore, further research is needed to explore the potential of ChatGPT for self-directed learning. One potential solution involves utilizing learning analytics as a novel approach to examine various aspects of students' learning and support them in their individual endeavors [ 32 ]. This approach can bridge this gap by facilitating an in-depth analysis of how learners engage with ChatGPT, identifying trends in self-directed learning behavior, and assessing its influence on their outcomes.

Turning to the significant concerns, on the other hand, a fundamental challenge with LLM-based chatbots, including ChatGPT, is the accuracy and quality of the provided information and responses, as they provide false information as truth—a phenomenon often referred to as "hallucination" [ 3 , 49 ]. In this context, this review found that the provided information was not entirely satisfactory. Consequently, the utilization of chatbots presents potential concerns, such as generating and providing inaccurate or misleading information, especially for students who utilize it to support their learning. This finding aligns with other findings [ 6 , 30 , 35 , 40 ] which revealed that incorporating chatbots such as ChatGPT, into education presents challenges related to its accuracy and reliability due to its training on a large corpus of data, which may contain inaccuracies and the way users formulate or ask ChatGPT. Therefore, immediate action is needed to address these potential issues. One possible solution is to equip students with the necessary skills and competencies, which include a background understanding of how to use it effectively and the ability to assess and evaluate the information it generates, as the accuracy and the quality of the provided information depend on the input, its complexity, the topic, and the relevance of its training data [ 28 , 49 , 86 ]. However, it's also essential to examine how learners can be educated about how these models operate, the data used in their training, and how to recognize their limitations, challenges, and issues [ 79 ].

Furthermore, chatbots present a substantial challenge concerning maintaining academic integrity [ 20 , 56 ] and copyright violations [ 83 ], which are significant concerns in education. The review found that the potential misuse of ChatGPT might foster cheating, facilitate plagiarism, and threaten academic integrity. This issue is also affirmed by the research conducted by Basic et al. [ 7 ], who presented evidence that students who utilized ChatGPT in their writing assignments had more plagiarism cases than those who did not. These findings align with the conclusions drawn by Cotton et al. [ 13 ], Hisan and Amri [ 33 ] and Sullivan et al. [ 75 ], who revealed that the integration of chatbots such as ChatGPT into education poses a significant challenge to the preservation of academic integrity. Moreover, chatbots, including ChatGPT, have increased the difficulty in identifying plagiarism [ 47 , 67 , 76 ]. The findings from previous studies [ 1 , 84 ] indicate that AI-generated text often went undetected by plagiarism software, such as Turnitin. However, Turnitin and other similar plagiarism detection tools, such as ZeroGPT, GPTZero, and Copyleaks, have since evolved, incorporating enhanced techniques to detect AI-generated text, despite the possibility of false positives, as noted in different studies that have found these tools still not yet fully ready to accurately and reliably identify AI-generated text [ 10 , 51 ], and new novel detection methods may need to be created and implemented for AI-generated text detection [ 4 ]. This potential issue could lead to another concern, which is the difficulty of accurately evaluating student performance when they utilize chatbots such as ChatGPT assistance in their assignments. Consequently, the most LLM-driven chatbots present a substantial challenge to traditional assessments [ 64 ]. The findings from previous studies indicate the importance of rethinking, improving, and redesigning innovative assessment methods in the era of chatbots [ 14 , 20 , 64 , 75 ]. These methods should prioritize the process of evaluating students' ability to apply knowledge to complex cases and demonstrate comprehension, rather than solely focusing on the final product for assessment. Therefore, immediate action is needed to address these potential issues. One possible solution would be the development of clear guidelines, regulatory policies, and pedagogical guidance. These measures would help regulate the proper and ethical utilization of chatbots, such as ChatGPT, and must be established before their introduction to students [ 35 , 38 , 39 , 41 , 89 ].

In summary, our review has delved into the utilization of ChatGPT, a prominent example of chatbots, in education, addressing the question of how ChatGPT has been utilized in education. However, there remain significant gaps, which necessitate further research to shed light on this area.

7 Conclusions

This systematic review has shed light on the varied initial attempts at incorporating ChatGPT into education by both learners and educators, while also offering insights and considerations that can facilitate its effective and responsible use in future educational contexts. From the analysis of 14 selected studies, the review revealed the dual-edged impact of ChatGPT in educational settings. On the positive side, ChatGPT significantly aided the learning process in various ways. Learners have used it as a virtual intelligent assistant, benefiting from its ability to provide immediate feedback, on-demand answers, and easy access to educational resources. Additionally, it was clear that learners have used it to enhance their writing and language skills, engaging in practices such as generating ideas, composing essays, and performing tasks like summarizing, translating, paraphrasing texts, or checking grammar. Importantly, other learners have utilized it in supporting and facilitating their directed and personalized learning on a broad range of educational topics, assisting in understanding concepts and homework, providing structured learning plans, and clarifying assignments and tasks. Educators, on the other hand, found ChatGPT beneficial for enhancing productivity and efficiency. They used it for creating lesson plans, generating quizzes, providing additional resources, and answers learners' questions, which saved time and allowed for more dynamic and engaging teaching strategies and methodologies.

However, the review also pointed out negative impacts. The results revealed that overuse of ChatGPT could decrease innovative capacities and collaborative learning among learners. Specifically, relying too much on ChatGPT for quick answers can inhibit learners' critical thinking and problem-solving skills. Learners might not engage deeply with the material or consider multiple solutions to a problem. This tendency was particularly evident in group projects, where learners preferred consulting ChatGPT individually for solutions over brainstorming and collaborating with peers, which negatively affected their teamwork abilities. On a broader level, integrating ChatGPT into education has also raised several concerns, including the potential for providing inaccurate or misleading information, issues of inequity in access, challenges related to academic integrity, and the possibility of misusing the technology.

Accordingly, this review emphasizes the urgency of developing clear rules, policies, and regulations to ensure ChatGPT's effective and responsible use in educational settings, alongside other chatbots, by both learners and educators. This requires providing well-structured training to educate them on responsible usage and understanding its limitations, along with offering sufficient background information. Moreover, it highlights the importance of rethinking, improving, and redesigning innovative teaching and assessment methods in the era of ChatGPT. Furthermore, conducting further research and engaging in discussions with policymakers and stakeholders are essential steps to maximize the benefits for both educators and learners and ensure academic integrity.

It is important to acknowledge that this review has certain limitations. Firstly, the limited inclusion of reviewed studies can be attributed to several reasons, including the novelty of the technology, as new technologies often face initial skepticism and cautious adoption; the lack of clear guidelines or best practices for leveraging this technology for educational purposes; and institutional or governmental policies affecting the utilization of this technology in educational contexts. These factors, in turn, have affected the number of studies available for review. Secondly, the utilization of the original version of ChatGPT, based on GPT-3 or GPT-3.5, implies that new studies utilizing the updated version, GPT-4 may lead to different findings. Therefore, conducting follow-up systematic reviews is essential once more empirical studies on ChatGPT are published. Additionally, long-term studies are necessary to thoroughly examine and assess the impact of ChatGPT on various educational practices.

Despite these limitations, this systematic review has highlighted the transformative potential of ChatGPT in education, revealing its diverse utilization by learners and educators alike and summarized the benefits of incorporating it into education, as well as the forefront critical concerns and challenges that must be addressed to facilitate its effective and responsible use in future educational contexts. This review could serve as an insightful resource for practitioners who seek to integrate ChatGPT into education and stimulate further research in the field.

Data availability

The data supporting our findings are available upon request.

Abbreviations

• Artificial intelligence

AI in education

Large language model

Artificial neural networks

Chat Generative Pre-Trained Transformer

Recurrent neural networks

Long short-term memory

Reinforcement learning from human feedback

Natural language processing

Preferred Reporting Items for Systematic Reviews and Meta-Analyses

AlAfnan MA, Dishari S, Jovic M, Lomidze K. ChatGPT as an educational tool: opportunities, challenges, and recommendations for communication, business writing, and composition courses. J Artif Intell Technol. 2023. https://doi.org/10.37965/jait.2023.0184 .

Article   Google Scholar  

Ali JKM, Shamsan MAA, Hezam TA, Mohammed AAQ. Impact of ChatGPT on learning motivation. J Engl Stud Arabia Felix. 2023;2(1):41–9. https://doi.org/10.56540/jesaf.v2i1.51 .

Alkaissi H, McFarlane SI. Artificial hallucinations in ChatGPT: implications in scientific writing. Cureus. 2023. https://doi.org/10.7759/cureus.35179 .

Anderson N, Belavý DL, Perle SM, Hendricks S, Hespanhol L, Verhagen E, Memon AR. AI did not write this manuscript, or did it? Can we trick the AI text detector into generated texts? The potential future of ChatGPT and AI in sports & exercise medicine manuscript generation. BMJ Open Sport Exerc Med. 2023;9(1): e001568. https://doi.org/10.1136/bmjsem-2023-001568 .

Ausat AMA, Massang B, Efendi M, Nofirman N, Riady Y. Can chat GPT replace the role of the teacher in the classroom: a fundamental analysis. J Educ. 2023;5(4):16100–6.

Google Scholar  

Baidoo-Anu D, Ansah L. Education in the Era of generative artificial intelligence (AI): understanding the potential benefits of ChatGPT in promoting teaching and learning. Soc Sci Res Netw. 2023. https://doi.org/10.2139/ssrn.4337484 .

Basic Z, Banovac A, Kruzic I, Jerkovic I. Better by you, better than me, chatgpt3 as writing assistance in students essays. 2023. arXiv preprint arXiv:2302.04536 .‏

Baskara FR. The promises and pitfalls of using chat GPT for self-determined learning in higher education: an argumentative review. Prosiding Seminar Nasional Fakultas Tarbiyah dan Ilmu Keguruan IAIM Sinjai. 2023;2:95–101. https://doi.org/10.47435/sentikjar.v2i0.1825 .

Behera RK, Bala PK, Dhir A. The emerging role of cognitive computing in healthcare: a systematic literature review. Int J Med Inform. 2019;129:154–66. https://doi.org/10.1016/j.ijmedinf.2019.04.024 .

Chaka C. Detecting AI content in responses generated by ChatGPT, YouChat, and Chatsonic: the case of five AI content detection tools. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.2.12 .

Chiu TKF, Xia Q, Zhou X, Chai CS, Cheng M. Systematic literature review on opportunities, challenges, and future research recommendations of artificial intelligence in education. Comput Educ Artif Intell. 2023;4:100118. https://doi.org/10.1016/j.caeai.2022.100118 .

Choi EPH, Lee JJ, Ho M, Kwok JYY, Lok KYW. Chatting or cheating? The impacts of ChatGPT and other artificial intelligence language models on nurse education. Nurse Educ Today. 2023;125:105796. https://doi.org/10.1016/j.nedt.2023.105796 .

Cotton D, Cotton PA, Shipway JR. Chatting and cheating: ensuring academic integrity in the era of ChatGPT. Innov Educ Teach Int. 2023. https://doi.org/10.1080/14703297.2023.2190148 .

Crawford J, Cowling M, Allen K. Leadership is needed for ethical ChatGPT: Character, assessment, and learning using artificial intelligence (AI). J Univ Teach Learn Pract. 2023. https://doi.org/10.53761/1.20.3.02 .

Creswell JW. Educational research: planning, conducting, and evaluating quantitative and qualitative research [Ebook]. 4th ed. London: Pearson Education; 2015.

Curry D. ChatGPT Revenue and Usage Statistics (2023)—Business of Apps. 2023. https://www.businessofapps.com/data/chatgpt-statistics/

Day T. A preliminary investigation of fake peer-reviewed citations and references generated by ChatGPT. Prof Geogr. 2023. https://doi.org/10.1080/00330124.2023.2190373 .

De Castro CA. A Discussion about the Impact of ChatGPT in education: benefits and concerns. J Bus Theor Pract. 2023;11(2):p28. https://doi.org/10.22158/jbtp.v11n2p28 .

Deng X, Yu Z. A meta-analysis and systematic review of the effect of Chatbot technology use in sustainable education. Sustainability. 2023;15(4):2940. https://doi.org/10.3390/su15042940 .

Eke DO. ChatGPT and the rise of generative AI: threat to academic integrity? J Responsib Technol. 2023;13:100060. https://doi.org/10.1016/j.jrt.2023.100060 .

Elmoazen R, Saqr M, Tedre M, Hirsto L. A systematic literature review of empirical research on epistemic network analysis in education. IEEE Access. 2022;10:17330–48. https://doi.org/10.1109/access.2022.3149812 .

Farrokhnia M, Banihashem SK, Noroozi O, Wals AEJ. A SWOT analysis of ChatGPT: implications for educational practice and research. Innov Educ Teach Int. 2023. https://doi.org/10.1080/14703297.2023.2195846 .

Fergus S, Botha M, Ostovar M. Evaluating academic answers generated using ChatGPT. J Chem Educ. 2023;100(4):1672–5. https://doi.org/10.1021/acs.jchemed.3c00087 .

Fink A. Conducting research literature reviews: from the Internet to Paper. Incorporated: SAGE Publications; 2010.

Firaina R, Sulisworo D. Exploring the usage of ChatGPT in higher education: frequency and impact on productivity. Buletin Edukasi Indonesia (BEI). 2023;2(01):39–46. https://doi.org/10.56741/bei.v2i01.310 .

Firat, M. (2023). How chat GPT can transform autodidactic experiences and open education.  Department of Distance Education, Open Education Faculty, Anadolu Unive .‏ https://orcid.org/0000-0001-8707-5918

Firat M. What ChatGPT means for universities: perceptions of scholars and students. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.1.22 .

Fuchs K. Exploring the opportunities and challenges of NLP models in higher education: is Chat GPT a blessing or a curse? Front Educ. 2023. https://doi.org/10.3389/feduc.2023.1166682 .

García-Peñalvo FJ. La percepción de la inteligencia artificial en contextos educativos tras el lanzamiento de ChatGPT: disrupción o pánico. Educ Knowl Soc. 2023;24: e31279. https://doi.org/10.14201/eks.31279 .

Gilson A, Safranek CW, Huang T, Socrates V, Chi L, Taylor A, Chartash D. How does ChatGPT perform on the United States medical Licensing examination? The implications of large language models for medical education and knowledge assessment. JMIR Med Educ. 2023;9: e45312. https://doi.org/10.2196/45312 .

Hashana AJ, Brundha P, Ayoobkhan MUA, Fazila S. Deep Learning in ChatGPT—A Survey. In   2023 7th international conference on trends in electronics and informatics (ICOEI) . 2023. (pp. 1001–1005). IEEE. https://doi.org/10.1109/icoei56765.2023.10125852

Hirsto L, Saqr M, López-Pernas S, Valtonen T. (2022). A systematic narrative review of learning analytics research in K-12 and schools.  Proceedings . https://ceur-ws.org/Vol-3383/FLAIEC22_paper_9536.pdf

Hisan UK, Amri MM. ChatGPT and medical education: a double-edged sword. J Pedag Educ Sci. 2023;2(01):71–89. https://doi.org/10.13140/RG.2.2.31280.23043/1 .

Hopkins AM, Logan JM, Kichenadasse G, Sorich MJ. Artificial intelligence chatbots will revolutionize how cancer patients access information: ChatGPT represents a paradigm-shift. JNCI Cancer Spectr. 2023. https://doi.org/10.1093/jncics/pkad010 .

Househ M, AlSaad R, Alhuwail D, Ahmed A, Healy MG, Latifi S, Sheikh J. Large Language models in medical education: opportunities, challenges, and future directions. JMIR Med Educ. 2023;9: e48291. https://doi.org/10.2196/48291 .

Ilkka T. The impact of artificial intelligence on learning, teaching, and education. Minist de Educ. 2018. https://doi.org/10.2760/12297 .

Iqbal N, Ahmed H, Azhar KA. Exploring teachers’ attitudes towards using CHATGPT. Globa J Manag Adm Sci. 2022;3(4):97–111. https://doi.org/10.46568/gjmas.v3i4.163 .

Irfan M, Murray L, Ali S. Integration of Artificial intelligence in academia: a case study of critical teaching and learning in Higher education. Globa Soc Sci Rev. 2023;8(1):352–64. https://doi.org/10.31703/gssr.2023(viii-i).32 .

Jeon JH, Lee S. Large language models in education: a focus on the complementary relationship between human teachers and ChatGPT. Educ Inf Technol. 2023. https://doi.org/10.1007/s10639-023-11834-1 .

Khan RA, Jawaid M, Khan AR, Sajjad M. ChatGPT—Reshaping medical education and clinical management. Pak J Med Sci. 2023. https://doi.org/10.12669/pjms.39.2.7653 .

King MR. A conversation on artificial intelligence, Chatbots, and plagiarism in higher education. Cell Mol Bioeng. 2023;16(1):1–2. https://doi.org/10.1007/s12195-022-00754-8 .

Kooli C. Chatbots in education and research: a critical examination of ethical implications and solutions. Sustainability. 2023;15(7):5614. https://doi.org/10.3390/su15075614 .

Kuhail MA, Alturki N, Alramlawi S, Alhejori K. Interacting with educational chatbots: a systematic review. Educ Inf Technol. 2022;28(1):973–1018. https://doi.org/10.1007/s10639-022-11177-3 .

Lee H. The rise of ChatGPT: exploring its potential in medical education. Anat Sci Educ. 2023. https://doi.org/10.1002/ase.2270 .

Li L, Subbareddy R, Raghavendra CG. AI intelligence Chatbot to improve students learning in the higher education platform. J Interconnect Netw. 2022. https://doi.org/10.1142/s0219265921430325 .

Limna P. A Review of Artificial Intelligence (AI) in Education during the Digital Era. 2022. https://ssrn.com/abstract=4160798

Lo CK. What is the impact of ChatGPT on education? A rapid review of the literature. Educ Sci. 2023;13(4):410. https://doi.org/10.3390/educsci13040410 .

Luo W, He H, Liu J, Berson IR, Berson MJ, Zhou Y, Li H. Aladdin’s genie or pandora’s box For early childhood education? Experts chat on the roles, challenges, and developments of ChatGPT. Early Educ Dev. 2023. https://doi.org/10.1080/10409289.2023.2214181 .

Meyer JG, Urbanowicz RJ, Martin P, O’Connor K, Li R, Peng P, Moore JH. ChatGPT and large language models in academia: opportunities and challenges. Biodata Min. 2023. https://doi.org/10.1186/s13040-023-00339-9 .

Mhlanga D. Open AI in education, the responsible and ethical use of ChatGPT towards lifelong learning. Soc Sci Res Netw. 2023. https://doi.org/10.2139/ssrn.4354422 .

Neumann, M., Rauschenberger, M., & Schön, E. M. (2023). “We Need To Talk About ChatGPT”: The Future of AI and Higher Education.‏ https://doi.org/10.1109/seeng59157.2023.00010

Nolan B. Here are the schools and colleges that have banned the use of ChatGPT over plagiarism and misinformation fears. Business Insider . 2023. https://www.businessinsider.com

O’Leary DE. An analysis of three chatbots: BlenderBot, ChatGPT and LaMDA. Int J Intell Syst Account, Financ Manag. 2023;30(1):41–54. https://doi.org/10.1002/isaf.1531 .

Okoli C. A guide to conducting a standalone systematic literature review. Commun Assoc Inf Syst. 2015. https://doi.org/10.17705/1cais.03743 .

OpenAI. (2023). https://openai.com/blog/chatgpt

Perkins M. Academic integrity considerations of AI large language models in the post-pandemic era: ChatGPT and beyond. J Univ Teach Learn Pract. 2023. https://doi.org/10.53761/1.20.02.07 .

Plevris V, Papazafeiropoulos G, Rios AJ. Chatbots put to the test in math and logic problems: A preliminary comparison and assessment of ChatGPT-3.5, ChatGPT-4, and Google Bard. arXiv (Cornell University) . 2023. https://doi.org/10.48550/arxiv.2305.18618

Rahman MM, Watanobe Y (2023) ChatGPT for education and research: opportunities, threats, and strategies. Appl Sci 13(9):5783. https://doi.org/10.3390/app13095783

Ram B, Verma P. Artificial intelligence AI-based Chatbot study of ChatGPT, google AI bard and baidu AI. World J Adv Eng Technol Sci. 2023;8(1):258–61. https://doi.org/10.30574/wjaets.2023.8.1.0045 .

Rasul T, Nair S, Kalendra D, Robin M, de Oliveira Santini F, Ladeira WJ, Heathcote L. The role of ChatGPT in higher education: benefits, challenges, and future research directions. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.1.29 .

Ratnam M, Sharm B, Tomer A. ChatGPT: educational artificial intelligence. Int J Adv Trends Comput Sci Eng. 2023;12(2):84–91. https://doi.org/10.30534/ijatcse/2023/091222023 .

Ray PP. ChatGPT: a comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet Things Cyber-Phys Syst. 2023;3:121–54. https://doi.org/10.1016/j.iotcps.2023.04.003 .

Roumeliotis KI, Tselikas ND. ChatGPT and Open-AI models: a preliminary review. Future Internet. 2023;15(6):192. https://doi.org/10.3390/fi15060192 .

Rudolph J, Tan S, Tan S. War of the chatbots: Bard, Bing Chat, ChatGPT, Ernie and beyond. The new AI gold rush and its impact on higher education. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.1.23 .

Ruiz LMS, Moll-López S, Nuñez-Pérez A, Moraño J, Vega-Fleitas E. ChatGPT challenges blended learning methodologies in engineering education: a case study in mathematics. Appl Sci. 2023;13(10):6039. https://doi.org/10.3390/app13106039 .

Sallam M, Salim NA, Barakat M, Al-Tammemi AB. ChatGPT applications in medical, dental, pharmacy, and public health education: a descriptive study highlighting the advantages and limitations. Narra J. 2023;3(1): e103. https://doi.org/10.52225/narra.v3i1.103 .

Salvagno M, Taccone FS, Gerli AG. Can artificial intelligence help for scientific writing? Crit Care. 2023. https://doi.org/10.1186/s13054-023-04380-2 .

Saqr M, López-Pernas S, Helske S, Hrastinski S. The longitudinal association between engagement and achievement varies by time, students’ profiles, and achievement state: a full program study. Comput Educ. 2023;199:104787. https://doi.org/10.1016/j.compedu.2023.104787 .

Saqr M, Matcha W, Uzir N, Jovanović J, Gašević D, López-Pernas S. Transferring effective learning strategies across learning contexts matters: a study in problem-based learning. Australas J Educ Technol. 2023;39(3):9.

Schöbel S, Schmitt A, Benner D, Saqr M, Janson A, Leimeister JM. Charting the evolution and future of conversational agents: a research agenda along five waves and new frontiers. Inf Syst Front. 2023. https://doi.org/10.1007/s10796-023-10375-9 .

Shoufan A. Exploring students’ perceptions of CHATGPT: thematic analysis and follow-up survey. IEEE Access. 2023. https://doi.org/10.1109/access.2023.3268224 .

Sonderegger S, Seufert S. Chatbot-mediated learning: conceptual framework for the design of Chatbot use cases in education. Gallen: Institute for Educational Management and Technologies, University of St; 2022. https://doi.org/10.5220/0010999200003182 .

Book   Google Scholar  

Strzelecki A. To use or not to use ChatGPT in higher education? A study of students’ acceptance and use of technology. Interact Learn Environ. 2023. https://doi.org/10.1080/10494820.2023.2209881 .

Su J, Yang W. Unlocking the power of ChatGPT: a framework for applying generative AI in education. ECNU Rev Educ. 2023. https://doi.org/10.1177/20965311231168423 .

Sullivan M, Kelly A, McLaughlan P. ChatGPT in higher education: Considerations for academic integrity and student learning. J ApplLearn Teach. 2023;6(1):1–10. https://doi.org/10.37074/jalt.2023.6.1.17 .

Szabo A. ChatGPT is a breakthrough in science and education but fails a test in sports and exercise psychology. Balt J Sport Health Sci. 2023;1(128):25–40. https://doi.org/10.33607/bjshs.v127i4.1233 .

Taecharungroj V. “What can ChatGPT do?” analyzing early reactions to the innovative AI chatbot on Twitter. Big Data Cognit Comput. 2023;7(1):35. https://doi.org/10.3390/bdcc7010035 .

Tam S, Said RB. User preferences for ChatGPT-powered conversational interfaces versus traditional methods. Biomed Eng Soc. 2023. https://doi.org/10.58496/mjcsc/2023/004 .

Tedre M, Kahila J, Vartiainen H. (2023). Exploration on how co-designing with AI facilitates critical evaluation of ethics of AI in craft education. In: Langran E, Christensen P, Sanson J (Eds).  Proceedings of Society for Information Technology and Teacher Education International Conference . 2023. pp. 2289–2296.

Tlili A, Shehata B, Adarkwah MA, Bozkurt A, Hickey DT, Huang R, Agyemang B. What if the devil is my guardian angel: ChatGPT as a case study of using chatbots in education. Smart Learn Environ. 2023. https://doi.org/10.1186/s40561-023-00237-x .

Uddin SMJ, Albert A, Ovid A, Alsharef A. Leveraging CHATGPT to aid construction hazard recognition and support safety education and training. Sustainability. 2023;15(9):7121. https://doi.org/10.3390/su15097121 .

Valtonen T, López-Pernas S, Saqr M, Vartiainen H, Sointu E, Tedre M. The nature and building blocks of educational technology research. Comput Hum Behav. 2022;128:107123. https://doi.org/10.1016/j.chb.2021.107123 .

Vartiainen H, Tedre M. Using artificial intelligence in craft education: crafting with text-to-image generative models. Digit Creat. 2023;34(1):1–21. https://doi.org/10.1080/14626268.2023.2174557 .

Ventayen RJM. OpenAI ChatGPT generated results: similarity index of artificial intelligence-based contents. Soc Sci Res Netw. 2023. https://doi.org/10.2139/ssrn.4332664 .

Wagner MW, Ertl-Wagner BB. Accuracy of information and references using ChatGPT-3 for retrieval of clinical radiological information. Can Assoc Radiol J. 2023. https://doi.org/10.1177/08465371231171125 .

Wardat Y, Tashtoush MA, AlAli R, Jarrah AM. ChatGPT: a revolutionary tool for teaching and learning mathematics. Eurasia J Math, Sci Technol Educ. 2023;19(7):em2286. https://doi.org/10.29333/ejmste/13272 .

Webster J, Watson RT. Analyzing the past to prepare for the future: writing a literature review. Manag Inf Syst Quart. 2002;26(2):3.

Xiao Y, Watson ME. Guidance on conducting a systematic literature review. J Plan Educ Res. 2017;39(1):93–112. https://doi.org/10.1177/0739456x17723971 .

Yan D. Impact of ChatGPT on learners in a L2 writing practicum: an exploratory investigation. Educ Inf Technol. 2023. https://doi.org/10.1007/s10639-023-11742-4 .

Yu H. Reflection on whether Chat GPT should be banned by academia from the perspective of education and teaching. Front Psychol. 2023;14:1181712. https://doi.org/10.3389/fpsyg.2023.1181712 .

Zhu C, Sun M, Luo J, Li T, Wang M. How to harness the potential of ChatGPT in education? Knowl Manag ELearn. 2023;15(2):133–52. https://doi.org/10.34105/j.kmel.2023.15.008 .

Download references

The paper is co-funded by the Academy of Finland (Suomen Akatemia) Research Council for Natural Sciences and Engineering for the project Towards precision education: Idiographic learning analytics (TOPEILA), Decision Number 350560.

Author information

Authors and affiliations.

School of Computing, University of Eastern Finland, 80100, Joensuu, Finland

Yazid Albadarin, Mohammed Saqr, Nicolas Pope & Markku Tukiainen

You can also search for this author in PubMed   Google Scholar

Contributions

YA contributed to the literature search, data analysis, discussion, and conclusion. Additionally, YA contributed to the manuscript’s writing, editing, and finalization. MS contributed to the study’s design, conceptualization, acquisition of funding, project administration, allocation of resources, supervision, validation, literature search, and analysis of results. Furthermore, MS contributed to the manuscript's writing, revising, and approving it in its finalized state. NP contributed to the results, and discussions, and provided supervision. NP also contributed to the writing process, revisions, and the final approval of the manuscript in its finalized state. MT contributed to the study's conceptualization, resource management, supervision, writing, revising the manuscript, and approving it.

Corresponding author

Correspondence to Yazid Albadarin .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

See Table  4

The process of synthesizing the data presented in Table  4 involved identifying the relevant studies through a search process of databases (ERIC, Scopus, Web of Knowledge, Dimensions.ai, and lens.org) using specific keywords "ChatGPT" and "education". Following this, inclusion/exclusion criteria were applied, and data extraction was performed using Creswell's [ 15 ] coding techniques to capture key information and identify common themes across the included studies.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Albadarin, Y., Saqr, M., Pope, N. et al. A systematic literature review of empirical research on ChatGPT in education. Discov Educ 3 , 60 (2024). https://doi.org/10.1007/s44217-024-00138-2

Download citation

Received : 22 October 2023

Accepted : 10 May 2024

Published : 26 May 2024

DOI : https://doi.org/10.1007/s44217-024-00138-2

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Large language models
• Educational technology
• Systematic review
• Find a journal
• Publish with us
• Track your research

IEEE Account

• Change Username/Password
• Update Address

Purchase Details

• Payment Options
• Order History
• View Purchased Documents

Profile Information

• Communications Preferences
• Profession and Education
• Technical Interests
• US & Canada: +1 800 678 4333
• Worldwide: +1 732 981 0060
• Contact & Support
• About IEEE Xplore
• Accessibility
• Terms of Use
• Nondiscrimination Policy
• Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. © Copyright 2024 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• Clin Transl Med
• v.13(3); 2023 Mar
• PMC10028016

The future of ChatGPT in academic research and publishing: A commentary for clinical and translational medicine

1 School of Business and Law, Edith Cowan University, Perth Australia

2 Centre for Precision Health, Edith Cowan University, Perth Australia

ChatGPT, an artificial intelligence (AI)‐powered chatbot developed by OpenAI, is creating a buzz across all occupational sectors. Its name comes from its basis in the Generative Pretrained Transformer (GPT) language model. ChatGPT's most promising feature is its ability to offer human‐like responses to text input using deep learning techniques at a level far superior to any other AI model. Its rapid integration in various industries signals the public's burgeoning reliance on AI technology. Thus, it is essential to critically evaluate ChatGPT's potential impacts on academic clinical and translational medicine research.

1. ChatGPT'S INTRODUCTION TO MEDICAL RESEARCH

ChatGPT contains 175 billion parameters, making it one of the largest and most powerful models for AI processing available today—hence its growing use in different occupations. ChatGPT's responses are leaps and bounds above those from past AI programs, in no small part due to being more human‐like. ChatGPT has taken the business world by storm. It is easy to envision its expansion into clinical and translational medicine in the future. As such, experts must consider the potential effects of this technology in and beyond medical research.

ChatGPT has made its debut in the scientific literature through published papers and preprints. Although ChatGPT can undoubtedly benefit writers of all backgrounds, its limitations in medical research merit close attention. 1 The emerging use of ChatGPT has sparked an upheaval in the scientific community and ignited debates around the ethics of using AI to write scientific publications that can influence the decisions of physicians, researchers, and policymakers.

2. THE FACTUAL INACCURACIES OF ChatGPT

The most significant disadvantage of ChatGPT is that the information it compiles is not always accurate. This drawback is especially detrimental in academic publishing; after all, progress depends on sharing appropriate information. Presenting incorrect data in a scientific setting carries a great risk of harm. For example, research influences how personal and community health concerns are treated and managed.

The data which ChatGPT uses provide information from 2021 and earlier. The chatbot does not currently consider information reported in 2022 onward. 2 For a field that is driven by recent advances to boost knowledge, enhance interventions, and formulate evidence‐based policies, this year‐long (and growing) information gap is a stark hindrance. If scholars use ChatGPT to create content, attempting to publish papers that contain false or outdated information will tarnish authors’ credibility among colleagues and peers.

3. ChatGPT: NOT SO EASY TO DETECT

A double‐edged sword with ChatGPT is the ability—or more accurately, the inability—of scholars to detect when other professionals have used it. Researchers at Northwestern University asked ChatGPT to write 50 medical‐research abstracts based on a set of articles published in medical journals. The authors then asked a group of medical researchers to spot the fabricated abstracts. 3 Problematic results emerged, with human reviewers able to correctly identify only 68% of the ChatGPT‐produced abstracts and 86% of the genuine abstracts. These findings confirm ChatGPT writes believable (albeit potentially inaccurate) scientific abstracts.

The results of this study bode well for those interested in employing ChatGPT to facilitate the writing process, as people reading their work likely will not realize it was AI‐generated. However, this possibility raises several concerns. Being unable to identify valid information comes with consequences. Scientists may follow flawed investigation routes, which translate into wasted research dollars and misleading results. For policymakers, the inability to detect false research may ground policy decisions in incorrect information that could have monumental effects on society.

Due to these implications, the future of academic and scientific publishing may soon hold policies that forbid AI‐generated content. Those who use ChatGPT in any capacity will need to be aware of these mandates. The 40th International Conference on Machine Learning already banned papers written by AI tools, including ChatGPT. 4 The Science family of journals is also updating their license and Editorial Policies to specify that they will not allow ChatGPT‐produced text. They explained their stance in an editorial, stating that most cases of scientific misconduct arise from inadequate human attention, and permitting ChatGPT‐generated content significantly increases this risk. 5

4. AN AIDE FOR SCIENTIFIC INNOVATION

Not all ChatGPT‐related matters have elicited concern within the scientific research field. A February 2023 article in Nature described computational biologists’ use of ChatGPT to improve completed research papers. In just five minutes, the biologists received a review of their manuscript that increased readability and spotted equation‐based mistakes. During a trial with three manuscripts, the team's use of ChatGPT was not always smooth, but the final output returned better‐edited manuscripts. 6

Using ChatGPT for this purpose bypasses the scientific community's primary concerns surrounding AI and its use of inaccurate or outdated information. Because computational biologists initially wrote the manuscripts, the information was already accurate and up to date. ChatGPT can help increase researchers’ productivity and content quality. If scientists can spend less time editing their work, they can devote more time to advancing the field of medicine.

Considering these benefits, ChatGPT can prove invaluable for researchers looking to verify answers or identify problems in their work. It is important to remember that, as of now, ChatGPT is not sufficiently trained on specialized content to be able to fact‐check technical topics. 7

5. ChatGPT IN SCIENTIFIC RESEARCH AND PUBLISHING: THE PROS AND CONS

Experts anticipate that the technology and programs integrating ChatGPT will serve as precursors to more advanced AI systems. In the meantime, this chatbot can play a supportive role in academic and scientific publishing, primarily for editing. Even so, those who use ChatGPT must be aware of its limitations.

As it stands, ChatGPT cannot be relied upon to provide correct facts or produce reliable references, as stated by a January editorial in Nature Machine Intelligence . 8 Accepting the limitations of ChatGPT and using it only for certain tasks allows researchers to delegate tedious jobs, such as manuscript editing, to the AI model while avoiding catastrophes such as the publication of false information.

As ChatGPT becomes more commonplace, it will be crucial to calibrate expectations about its capabilities and acknowledge that it cannot take on every job. Especially in the academic research field, any tasks in need of specialized subject knowledge or innovative ideas and opinions still require a genuine human touch that cannot be replaced by AI.

6. ChatGPT AND CLINICAL AND TRANSLATIONAL MEDICINE

Our conclusions regarding ChatGPT and its applications in scientific research focus on a high‐impact journal– Clinical and Translational Medicine –that aims to promote, accelerate, and translate preclinical research for clinical applications. This journal highlights the importance of clinical and translational medicine research in the name of promoting the safety and efficacy of discoveries that proceed to human trials, reflecting the notion of ‘bench to bedside.’ 9 Implementing ChatGPT in its present iteration must be pursued with extreme caution given the tool's evolving limitations and capabilities when it comes to providing reliable information. Can AI replace human input? We concur with H. Holden Thorp's position 5 on ChatGPT in that “ChatGPT is fun, but not an author” (p. 313). Scientists might be able to use well‐developed AI tools to increase work efficiency for tasks such as proofreading and manuscript checks. In the future, AI‐based tools may become recognized for their contributions to broader areas of scientific research, depending on their abilities to support human input. The boundaries between research ethics and the moral use of AI in health research 10 need to be further explored to establish guidelines. All researchers and contributors must understand what AI can and cannot do. Therefore, editors and editorial board members should continue monitoring ChatGPT's applications in academic research to draft journal policies that inform contributors of best practices. Doing so will ensure that Clinical and Translational Medicine can maintain an image of integrity by publishing timely and accurate research that makes meaningful contributions. After all, research excellence is gauged by ethics and integrity.

CONFLICT OF INTEREST STATEMENT

The authors declare no conflict of interest.

Wen J, Wang W. The future of ChatGPT in academic research and publishing: A commentary for clinical and translational medicine . Clin Transl Med . 2023; 13 :e1207. 10.1002/ctm2.1207 [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]

Have a language expert improve your writing

Check your paper for plagiarism in 10 minutes, generate your apa citations for free.

• Knowledge Base

Using AI tools

How to Write a Paper with ChatGPT | Tips & Examples

Published on August 17, 2023 by Koen Driessen . Revised on November 16, 2023.

A good research paper demonstrates your academic writing skills and knowledge of your chosen topic.

Your research paper should be based on in-depth independent research. However, generative AI tools like ChatGPT can be effectively used throughout the research process to:

• Brainstorm research questions
• Develop a methodology
• Create an outline
• Find sources
• Summarize and paraphrase text
• Provide feedback

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

Brainstorming research questions, developing a methodology, creating an outline, finding sources, summarizing or paraphrasing text, receiving feedback, other interesting articles, frequently asked questions.

You can use ChatGPT to help formulate research questions , brainstorm potential thesis statements , or narrow down a broad subject area to a specific topic that interests you.

However, make sure that the outputs make sense and meet the requirements of your assignment. You can adapt these outputs manually, or use further prompts to ensure they meet your needs. For more information, see our tips for creating effective ChatGPT prompts .

• Generate three possible research questions for a research paper on the following topic: “The role of virtual reality in enhancing training and skill development in various industries.”
• “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods across different industries?”
• “How does the level of immersion in virtual reality training impact knowledge retention and skill transfer in fields such as medicine, aviation, and manufacturing?”
• “What are the key factors that influence the successful integration and adoption of virtual reality technology for training purposes in diverse industries, and what challenges hinder its widespread implementation?”

Check for common mistakes

Use the best grammar checker available to check for common mistakes in your text.

Fix mistakes for free

Your paper should clearly indicate the data collection and analysis methods you used in your research.

You can use ChatGPT to help decide what kind of research you will conduct (e.g., qualitative or quantitative ), how you will analyze the data, and how you will mitigate potential research bias .

Bear in mind that you should be able to rationalize your chosen methodology . For example, you should ensure that it is either a standard methodology in the field or can be justified.

• Suggest three quantitative research methods appropriate to the following question: “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”
• Experimental Study: Conduct a randomized controlled trial (RCT) where healthcare professionals are randomly assigned to either a virtual reality-based training group or a traditional training group. Both groups would receive training in specific healthcare tasks, and their cognitive and skill development outcomes would be measured and compared. Performance metrics, such as accuracy, speed, and efficiency, could be quantitatively assessed to determine the benefits of virtual reality-based training over traditional methods.
• Survey Research: Design a comprehensive survey targeting healthcare professionals who have undergone both virtual reality-based training and traditional training. The survey could include Likert-scale questions and structured response options to gauge their perceived cognitive and skill development benefits from each training method. Additionally, open-ended questions could be included to gather qualitative insights on specific strengths and weaknesses of each training approach.
• Task Performance Analysis: Implement a task-based assessment that simulates real-life healthcare scenarios, where participants are evaluated on their ability to handle critical situations. Participants would go through both virtual reality-based training and traditional training before being assessed in the simulated scenarios. Their performance in the assessment could be objectively measured using predefined criteria, allowing for a quantitative comparison of skill development between the two training methods.

A clear outline can help structure your paper, organize your arguments effectively, and make your research more efficient.

You can use generative AI tools like ChatGPT to formulate a potential outline to help guide your research. You can be as specific as you like, giving an overview of your research objectives , main arguments, and any evidence you intend to include in your paper.

However, ChatGPT outputs sometimes contain factual inaccuracies. It’s important to check the headings and subheadings suggested in the output and adapt them to meet your needs.

• Create an outline for an academic research paper with the following research question:“What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”The paper will be about 10 pages long.

A. Theoretical basis for cognitive and skill development in training

B. Application of cognitive theories to virtual reality-based training

C. The role of immersive learning environments in skill acquisition

D. Conceptual framework for the study

IV. Research Methodology

A. Research design and approach (e.g., quasi-experimental, pre-post intervention)

B. Selection of participants and sample size calculation

C. Description of the virtual reality-based training and traditional training programs

D. Instruments and measures for assessing cognitive and skill development

E. Data collection procedures and ethical considerations

V. Data Analysis

A. Overview of statistical methods used for data analysis

B. Treatment of data and data cleaning

C. Quantitative analysis of cognitive and skill development outcomes

D. Presentation of findings with charts and tables

VI. Results

A. Presentation of the results of the cognitive and skill development assessments

B. Comparison of outcomes between virtual reality-based training and traditional training

C. Statistical significance and effect size analysis

D. Interpretation of the results and implications

VII. Discussion

A. Interpretation of findings in the context of the research question

B. Comparison of results with existing literature

C. Explanation of how virtual reality-based training impacts cognitive processes and skill development

D. Limitations of the study and areas for future research

VIII. Practical Implications

A. Practical applications of virtual reality-based training in healthcare settings

B. Recommendations for integrating virtual reality training in healthcare education

C. Benefits of virtual reality for continuous professional development in healthcare

IX. Conclusion

A. Summary of key findings

B. Reiteration of the research question and hypothesis

C. Contributions of the study to the field of healthcare training

D. Concluding remarks

X. References

You can use ChatGPT to help find sources relevant to your research. However, it’s important to be aware of the limitations of ChatGPT (for example, it occasionally cites nonexistent sources).

Instead of asking ChatGPT for specific source recommendations, try asking it for recommendations on the types of sources relevant to your research topic. You can also use it to generate a list of relevant keywords to use in your literature search.

• What types of sources could I use to write a research paper on the following research question?“What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”
• Academic Journals: Peer-reviewed journals are valuable sources of scholarly research. Look for articles in medical education, cognitive psychology, virtual reality applications in healthcare, and technology-enhanced learning.
• Research Studies: Seek out published research studies that specifically investigate the impact of virtual reality-based training on cognitive and skill development in healthcare professionals.
• Systematic Reviews and Meta-Analyses: These studies provide comprehensive overviews of existing research on a specific topic, making them a valuable source for summarizing and analyzing the overall evidence.
• Books and Book Chapters: Academic books and book chapters authored by experts in the fields of medical education, virtual reality, cognitive science, or instructional design can provide in-depth insights and theoretical foundations.
• Conference Proceedings: Proceedings from relevant conferences and symposiums may present the latest findings and advancements in virtual reality-based training and healthcare education.
• Educational Institution Websites: Universities and medical schools often publish research papers, case studies, and whitepapers related to medical education and virtual reality training.
• Industry Reports: Reports and whitepapers from healthcare organizations or technology companies exploring the benefits of virtual reality-based training in the healthcare sector.
• Government and Non-profit Organizations: Look for reports and publications from government agencies and non-profit organizations that focus on medical education and healthcare training.
• Online Databases: Utilize academic databases such as PubMed, Google Scholar, IEEE Xplore, and ScienceDirect to search for peer-reviewed research articles and conference papers.
• Expert Interviews: If possible, conduct interviews with experts in medical education, cognitive science, and virtual reality to gain valuable insights and perspectives.
• Surveys and Polls: Refer to reputable surveys and polls related to virtual reality-based training in the healthcare industry for additional statistical data.

Don't submit your assignments before you do this

The academic proofreading tool has been trained on 1000s of academic texts. Making it the most accurate and reliable proofreading tool for students. Free citation check included.

Try for free

You can use ChatGPT to paraphrase or summarize text. This can help you to condense sources to their most important points and explore new ways of expressing your ideas.

Alternatively you can use the more specialized tools featured on Scribbr’s AI writing resources page (including Scribbr’s free text summarizer  and  Scribbr’s free paraphrasing tool ) which are designed specifically for these purposes and will give a smoother user experience.

• Provide a short summary of the following text:“One of the most profound applications of VR in healthcare is its use in surgical training. Traditionally, surgical training has relied on a combination of didactic lectures, observation of procedures, and hands-on experience in the operating room. However, these methods may not provide the ideal environment for novices to develop the necessary dexterity and spatial understanding essential for complex surgeries. VR overcomes these limitations by offering immersive, true-to-life simulations that allow surgeons to navigate through intricate anatomical structures, practice incisions, and learn to manage unexpected challenges that may arise during surgeries. This hands-on experience in a risk-free environment not only enhances technical skills but also builds confidence and reduces the learning curve for new surgical techniques.”
• Virtual Reality (VR) has a profound impact on healthcare, particularly in surgical training, as it provides immersive simulations that help surgeons develop dexterity, spatial understanding, and confidence for complex surgeries in a risk-free environment, ultimately enhancing their technical skills and reducing the learning curve.

When you’ve finished writing your research paper, you can use ChatGPT to receive feedback. You can be as specific as you like, selecting particular aspects the output should focus on (e.g., tone, clarity of structure, appropriateness of evidence to support your arguments).

You can also use ChatGPT to check grammar, spelling, and punctuation. However, it’s not designed for this purpose and occasionally misses errors. We recommend using a more specialized tool like Scribbr’s free grammar checker . Or, for more comprehensive feedback, Scribbr’s proofreading and editing service .

• Feedback the above text with regard to appropriateness of evidence and coherence of structure.
• The research paper demonstrates a well-structured and coherent presentation of the cognitive and skill development benefits of VR-based surgical training. The introduction effectively sets the context and rationale, while the literature review incorporates relevant historical and empirical evidence. The theoretical framework strengthens the foundation for the analysis.The methodology section could provide more details on the research design and study selection criteria. However, the sections on cognitive and skill development benefits present compelling evidence, supported by appropriate sub-sections.The exploration of improved patient outcomes lacks concrete examples but effectively outlines potential benefits. The section on challenges and future directions raises relevant points, but suggestions for solutions could enhance practicality.Overall, the paper combines theoretical, empirical, and practical evidence, offering a well-rounded approach. It establishes the significance of VR-based surgical training and concludes with a concise summary of key findings.

If you want more tips on using AI tools , understanding plagiarism , and citing sources , make sure to check out some of our other articles with explanations, examples, and formats.

• Citing ChatGPT
• Best grammar checker
• Best paraphrasing tool
• ChatGPT in your studies
• Is ChatGPT trustworthy?
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

• Citation styles
• In-text citation
• Citation examples
• Annotated bibliography

Yes, you can use ChatGPT to summarize text . This can help you understand complex information more easily, summarize the central argument of your own paper, or clarify your research question.

You can also use Scribbr’s free text summarizer , which is designed specifically for this purpose.

Yes, you can use ChatGPT to paraphrase text to help you express your ideas more clearly, explore different ways of phrasing your arguments, and avoid repetition.

However, it’s not specifically designed for this purpose. We recommend using a specialized tool like Scribbr’s free paraphrasing tool , which will provide a smoother user experience.

No, it’s not a good idea to do so in general—first, because it’s normally considered plagiarism or academic dishonesty to represent someone else’s work as your own (even if that “someone” is an AI language model). Even if you cite ChatGPT , you’ll still be penalized unless this is specifically allowed by your university . Institutions may use AI detectors to enforce these rules.

Second, ChatGPT can recombine existing texts, but it cannot really generate new knowledge. And it lacks specialist knowledge of academic topics. Therefore, it is not possible to obtain original research results, and the text produced may contain factual errors.

However, you can usually still use ChatGPT for assignments in other ways, as a source of inspiration and feedback.

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the “Cite this Scribbr article” button to automatically add the citation to our free Citation Generator.

Driessen, K. (2023, November 16). How to Write a Paper with ChatGPT | Tips & Examples. Scribbr. Retrieved August 21, 2024, from https://www.scribbr.com/ai-tools/chatgpt-research-paper/

Is this article helpful?

Koen Driessen

Other students also liked, how to write good chatgpt prompts, chatgpt citations | formats & examples, what are the limitations of chatgpt, "i thought ai proofreading was useless but..".

I've been using Scribbr for years now and I know it's a service that won't disappoint. It does a good job spotting mistakes”

share this!

August 21, 2024

This article has been reviewed according to Science X's editorial process and policies . Editors have highlighted the following attributes while ensuring the content's credibility:

fact-checked

peer-reviewed publication

trusted source

Study says ChatGPT could help people with creativity in everyday tasks

by University of Houston

ChatGPT, the generative artificial intelligence technology developed by OpenAI, could help humans with daily, creative tasks—even those typically thought to require the human ability to "read between the lines," according to new research by the University of Houston and Rice University. Its capability has proven to be superior compared to traditional Google search or even human brainstorming without any technical assistance, the study authors argue.

The paper , "An empirical investigation of the impact of ChatGPT on creativity," published in Nature Human Behavior , details five experiments the research team performed on ChatGPT (GPT-3.5) designed to assess the creative ideation capabilities of the program.

The researchers asked participants to generate creative ideas using ChatGPT, Google or with no assistance. They then employed two groups of coders: participants from the same population and expert judges with more than five years of relevant business experience. Both groups of coders—blind to the conditions—rated the ideas generated by ChatGPT as superior in creativity.

The study indeed found that using ChatGPT can increase the creativity of responses to problem-solving tasks of daily life such as generating gift ideas, or repurposing unused items. ChatGPT's strength lies in its ability to bring together diverse concepts in a clear and coherent manner, according to the researchers. It can combine remotely related concepts into a cohesive form, the authors argue.

"Our results show that ChatGPT is highly effective at generating ideas that are incrementally new rather than radically new," wrote authors Byung Cheol Lee, assistant professor at UH's C.T. Bauer College of Business, and Jaeyeon (Jae) Chung, the William S. Mackey Jr. Distinguished Assistant Professor at Rice's Jones Graduate School of Business.

"This result stems from ChatGPT's proficiency in combining various concepts from its database rather than inventing entirely new concepts from scratch."

ChatGPT also showed competence in tasks that people expect to require empathy, according to the report.

"Prior beliefs have often emphasized the uniquely human ability to understand emotions, empathize and 'read between the lines,' leading to expectations that ChatGPT would fall short in scenarios that appear to require such emotional understanding," the authors wrote.

"Contrary to these expectations, however, our results show that ChatGPT demonstrates remarkable performance in these very tasks. This finding highlights ChatGPT's potential for assisting not only in analytical tasks but also in tasks that traditionally require emotional understanding."

Journal information: Nature Human Behaviour

Provided by University of Houston

Explore further

Feedback to editors

First visualization of valence electrons reveals fundamental nature of chemical bonding

9 minutes ago

The power of face time: Insights from zebra finch courtship shed light on later life learning

35 minutes ago

More academic freedom leads to more innovation, reports study

44 minutes ago

A maximally entangled quantum state with a fixed spectrum does not exist in the presence of noise, mathematician claims

45 minutes ago

Tissue fluidization during skin repair is crucial for wound healing, study reveals

54 minutes ago

Study shows effective regulation and monitoring is key to tackling emissions of a super-greenhouse gas

Self-repairing mitochondria use novel recycling system, study finds

Bacteria make thermally stable plastics similar to polystyrene and PET for the first time

New heaviest exotic antimatter nucleus discovered

Mobile species are 'glue' which connect different habitats together, study finds

Relevant physicsforums posts, today's fusion music: t square, cassiopeia, rei & kanade sato.

3 hours ago

Interesting anecdotes in the history of physics?

6 hours ago

Favorite songs (cont.)

10 hours ago

Cover songs versus the original track, which ones are better?

19 hours ago

Why are ABBA so popular?

21 hours ago

Song: Epiphany of the Physicist

Aug 20, 2024

More from Art, Music, History, and Linguistics

Related Stories

ChatGPT found to display lower concern for child development 'warning signs' than physicians

May 3, 2024

Think you're funny? ChatGPT might be funnier

Jul 3, 2024

ChatGPT shows poor performance in answering drug-related questions

Dec 12, 2023

Researchers highlight ChatGPT's role in bioinformatics and biomedical informatics

Jul 25, 2024

ChatGPT does not pass American College of Gastroenterology tests

May 23, 2023

AI tests into top 1% for original creative thinking

Jul 5, 2023

Recommended for you

Study suggests video game playing may have mental health benefits under some conditions

Study explains why laws are written in an incomprehensible style

Aug 19, 2024

Study finds gun violence in rural America rises as deer hunting season begins

Spread the love (online): Study reveals in-party positivity drives online engagement more than out-party hostility

How some states help residents avoid costly debt during hard times

Aug 16, 2024

Singing from memory unlocks a surprisingly common musical superpower

Aug 15, 2024

Let us know if there is a problem with our content

Use this form if you have come across a typo, inaccuracy or would like to send an edit request for the content on this page. For general inquiries, please use our contact form . For general feedback, use the public comments section below (please adhere to guidelines ).

Please select the most appropriate category to facilitate processing of your request

Thank you for taking time to provide your feedback to the editors.

Your feedback is important to us. However, we do not guarantee individual replies due to the high volume of messages.

E-mail the story

Your email address is used only to let the recipient know who sent the email. Neither your address nor the recipient's address will be used for any other purpose. The information you enter will appear in your e-mail message and is not retained by Phys.org in any form.

Newsletter sign up

Get weekly and/or daily updates delivered to your inbox. You can unsubscribe at any time and we'll never share your details to third parties.

More information Privacy policy

Donate and enjoy an ad-free experience

We keep our content available to everyone. Consider supporting Science X's mission by getting a premium account.

E-mail newsletter

Subscribe to the PwC Newsletter

Join the community, edit social preview.

Add a new code entry for this paper

Remove a code repository from this paper, mark the official implementation from paper authors, add a new evaluation result row.

Remove a task

Add a method.

• LINEAR REGRESSION

Remove a method

• LINEAR REGRESSION -

Edit Datasets

Evaluating research quality with large language models: an analysis of chatgpt's effectiveness with different settings and inputs.

13 Aug 2024  ·  Mike Thelwall · Edit social preview

Evaluating the quality of academic journal articles is a time consuming but critical task for national research evaluation exercises, appointments and promotion. It is therefore important to investigate whether Large Language Models (LLMs) can play a role in this process. This article assesses which ChatGPT inputs (full text without tables, figures and references; title and abstract; title only) produce better quality score estimates, and the extent to which scores are affected by ChatGPT models and system prompts. The results show that the optimal input is the article title and abstract, with average ChatGPT scores based on these (30 iterations on a dataset of 51 papers) correlating at 0.67 with human scores, the highest ever reported. ChatGPT 4o is slightly better than 3.5-turbo (0.66), and 4o-mini (0.66). The results suggest that article full texts might confuse LLM research quality evaluations, even though complex system instructions for the task are more effective than simple ones. Thus, whilst abstracts contain insufficient information for a thorough assessment of rigour, they may contain strong pointers about originality and significance. Finally, linear regression can be used to convert the model scores into the human scale scores, which is 31% more accurate than guessing.

Code Edit Add Remove Mark official

Tasks edit add remove, datasets edit, results from the paper edit add remove, methods edit add remove.

'ZDNET Recommends': What exactly does it mean?

ZDNET's recommendations are based on many hours of testing, research, and comparison shopping. We gather data from the best available sources, including vendor and retailer listings as well as other relevant and independent reviews sites. And we pore over customer reviews to find out what matters to real people who already own and use the products and services we’re assessing.

When you click through from our site to a retailer and buy a product or service, we may earn affiliate commissions. This helps support our work, but does not affect what we cover or how, and it does not affect the price you pay. Neither ZDNET nor the author are compensated for these independent reviews. Indeed, we follow strict guidelines that ensure our editorial content is never influenced by advertisers.

ZDNET's editorial team writes on behalf of you, our reader. Our goal is to deliver the most accurate information and the most knowledgeable advice possible in order to help you make smarter buying decisions on tech gear and a wide array of products and services. Our editors thoroughly review and fact-check every article to ensure that our content meets the highest standards. If we have made an error or published misleading information, we will correct or clarify the article. If you see inaccuracies in our content, please report the mistake via this form .

How to use ChatGPT to summarize a book, article, or research paper

AI chatbots like ChatGPT can be used to make summarizing long articles, research papers, and books an easier job. If you're tasked with writing a summary for school or work about a body of written text, and you're pinched for time, ChatGPT can help you understand the necessary components.

You should remember that ChatGPT is a tool that can help you further understand a topic, and it may not be in your best interest to have it write your work for you.

Also:   How to make ChatGPT provide sources and citations

If you're a student writing a research paper, someone who is keen to discover more about a lengthy article, or someone who wants to dive into a complicated subject, you can use ChatGPT to simplify the process.

How ChatGPT can create summaries for you

Materials needed : You'll need a device that can connect to the internet, an OpenAI account , and a basic understanding of the article, research paper, or book you want to summarize. 

Also:  This AI chatbot can sum up any PDF and answer any question you have about it

The process should take about one to three minutes.

1. Find your article, paper, or book to summarize

If you need ChatGPT to help summarize an article or research paper, find the body of text online and keep it open in a separate tab.

2. Open your web browser and log in to OpenAI

Open your web browser of choice and type in chat.openai.com/chat . 

Also: How to use ChatGPT to write Excel formulas

Log in or sign up for an account. 

3. Type your request

In the chat box, type in TLDR: followed by the title of the book you want summarized. TLDR stands for too long, didn't read. 

Also: How to use ChatGPT: Everything you need to know

You can also ask ChatGPT: "Summarize [book title]." 

You cannot paste a URL into ChatGPT. If you do so, you'll get a response explaining that the chatbot cannot access websites. If you want ChatGPT to summarize research, you'll need a basic understanding of the topic to ensure you aren't including inaccurate information in your report.

For example, if you're writing a paper about how twin sibling dynamics affect their marriages, you can ask ChatGPT: "Explain how twin relationships affect their marriages."

Also:   The best AI chatbots: ChatGPT and other noteworthy alternatives 

ChatGPT will offer you a few bullet points of both positive and negative effects a twin bond can have on the twins' marriages. You'll still need to read key points of the research, as ChatGPT won't provide you with specific statistics or scientific conclusions. But ChatGPT can help you understand the context surrounding the research you're interested in.

If you're having trouble comprehending specific passages in an article, book, or research paper, you can copy parts of the text and paste them into ChatGPT.

Think of this method as reshuffling the words you're currently reading to help you make more sense of the text in front of you.

This is an accurate summary of 'The Hunger Games: Mockingjay'.

What are ChatGPT's limitations?

If you're using ChatGPT to summarize an article, book, or piece of research, keep in mind that ChatGPT isn't aware of events that occurred after September 2021. 

Also:   4 things Claude AI can do that ChatGPT can't

ChatGPT is a large language model that uses queues and millions of data points to mimic human responses. This form of mimicry is why ChatGPT will answer questions even when it doesn't output the correct answer. So, make sure you're not using any information from ChatGPT without fact-checking it.

If you try to get around this obstacle and provide ChatGPT with an article that contains information post-2021, it might hallucinate. Here, I asked the chatbot to summarize an article about a new app I wrote about , and it made up a few details. 

Lemon8 is a new app from TikTok's parent company, ByteDance. Although the TikTok trend may exist, that's not what the article is about.

Can ChatGPT summarize a PDF?

Copying and pasting a URL into ChatGPT won't yield you the best results. If there is a specific paragraph or sentence you're struggling with, you can copy and paste it into ChatGPT and ask it to explain it to you. Still, it's best to read the PDF and use the chatbot as a summary tool and not as an educator. 

Also:  How to use ChatGPT to write code

If you're looking for an AI chatbot that you can regularly rely on to give you an accurate summary of a PDF, consider using ChatPDF . You can summarize up to three PDFs of up to 120 pages per day, and an upgraded plan is available for $5 per month.

Can ChatGPT summarize an email thread?

Sort of. If you want to copy and paste every single email, ChatGPT can summarize the thread's contents for you. It would be more helpful to scan an email thread yourself and ask ChatGPT to help you write a response based on the key points you know about the conversation. 

Editor's note: We've added additional context to the step concerning ChatGPT summarizing articles by URL. 

More on AI tools

How to use chatgpt to analyze pdfs (and more) for free, how to use chatgpt to write your resume, 5 ways chatgpt can help you write an essay.

Affiliate 💸

Get started free

Literature Review

How To Use ChatGPT For Research Papers in 6 Simple Steps

Discover how to use ChatGPT for research papers with 6 simple steps to streamline your writing process and enhance your academic work.

Aug 18, 2024

Think about how you’re staring down a research paper deadline. You have a topic in mind but don't know what the current literature looks like. You begin your search on Google Scholar only to feel overwhelmed by the dozens of articles that pop up. Between the dense academic language and highly technical jargon, knowing where to start is hard. If this sounds like a scenario you might encounter in the future, you're not alone. Many students dread writing research papers, and for good reason.  The process often requires extensive literature search before even drafting a paper, and starting from scratch can be daunting. Fortunately, emerging artificial intelligence tools like ChatGPT can help you navigate the complexities of research papers to ease your stress and even improve your grades in school. In this guide, we'll explore how ChatGPT for research papers can help you improve your literature search and write efficient research papers with fantastic study material. One tool that can help you achieve your research goals is Otio's AI research and writing partner. This artificial intelligence tool specializes in research papers and can help you find great sources, summarize complex information, and even generate sample outlines to help you get started.

Table Of Contents

What is a research paper, can i use chatgpt for research papers, 8 best chatgpt alternatives for research papers, is it ethical to use chatgpt for research papers, limitations of chatgpt, supercharge your researching ability with otio — try otio for free today.

A research paper is an expanded essay that presents your interpretation, evaluation, or argument. When writing an essay, you use everything you know and have thought about a subject. When you write a research paper, you build upon what you know about the subject and deliberately attempt to discover what experts know. A research paper involves surveying a field of knowledge to find the best possible information. And that survey can be orderly and focused if you know how to approach it. 

What's the Structure of a Research Paper?

The basic structure of a typical research paper includes Introduction, Methods, Results, and Discussion. Each section addresses a different objective. The problem they intend to address -- in other words, the research question -- in the Introduction; what they did to answer the question in Methodology; what they observed in the Results; and what they think the results mean in the Discussion. 

Absolutely! You can use ChatGPT to assist with writing research papers . The AI tool can help scholars brainstorm, create outlines, and develop a thesis for their papers. By breaking the task into manageable pieces, ChatGPT can make writing a research paper less intimidating. 

Related Reading

• Systematic Review Vs Meta Analysis • Impact Evaluation • How To Critique A Research Article • How To Synthesize Sources • Annotation Techniques • Skimming And Scanning • Types Of Literature Reviews • Literature Review Table • Literature Review Matrix • How To Increase Reading Speed And Comprehension • How To Read Research Papers • How To Summarize A Research Paper • Literature Gap

1. Nail Down Your Research Question or Hypothesis  

Start by zeroing in on the research question or hypothesis that you want to tackle in your paper. This will help you find relevant literature and organize your writing. 

2. Conduct a Thorough Literature Review  

Use ChatGPT to search for relevant scientific literature related to your research question or hypothesis. To get you started, ChatGPT can summarize existing research on your topic and identify gaps in the literature. 

3. Gather and Analyze Data  

Collect data through experiments, surveys, or other means. Then, use ChatGPT to help analyze and interpret your data and generate visualizations to support your findings. 

4. Organize Your Paper  

Use ChatGPT to help organize your paper by creating an outline, structuring your arguments, and ensuring that your paper is well-organized and flows logically. 

5. Draft Your Paper  

Use ChatGPT to generate draft sections of your paper, such as the introduction, methods, results, and discussion sections. However, review and edit the content generated by ChatGPT to ensure it aligns with your research and is written in your voice. 

6. Edit and Proofread Your Paper  

Use ChatGPT to help edit and proofread your paper for grammar, punctuation, and spelling errors. However, carefully review and make any necessary revisions to the content generated by ChatGPT to ensure accuracy and clarity.

1. Otio: Your AI Research Partner

Researchers and students today struggle with content overload. Otio solves this problem by providing researchers with one AI-native workspace . It helps them: 

1. Collect a wide range of data sources, from bookmarks, tweets, and extensive books to YouTube videos.

2. extract key takeaways with detailed ai-generated notes and source-grounded q&a chat., 3. create draft outputs using the sources you’ve collected. .

Otio helps you to go from the reading list to the first draft faster. Along with this, Otio also helps you write research papers/essays faster . Here are our top features that researchers love: AI-generated notes on all bookmarks (Youtube videos, PDFs, articles, etc.), Otio enables you to chat with individual links or entire knowledge bases, just like you chat with ChatGPT, as well as AI-assisted writing. 

2. ChatSonic: A Versatile Research Assistant

ChatSonic by Writesonic is an alternative to ChatGPT that offers advanced features like Google search integration, up-to-date factual content, voice commands, and image generation. Unlike ChatGPT, ChatSonic is integrated with Google, enabling it to provide the latest results on any search topic available on the internet. 

This advanced AI chatbot can assist with real-time data, image searches, and voice commands, making it a valuable tool for research and content creation. While ChatSonic has several advantages, including image generation and Google search data, it also has some limitations, such as pricing and limited access to the latest language models.

Google search integration for up-to-date content

Advanced AI chatbot features like voice commands and image generation

Easy access and user-friendly interface

Ideal for users already using Writesonic

Pricing may be a limitation for some users

Limited access to the latest language models

Useless features like templates and chat personalities

3. Gemini: A Multi-Modal Research Tool 

Gemini is an AI tool similar to ChatGPT that helps users brainstorm ideas, craft scripts, and generate content across various formats. Integrated with Google's search capabilities, Gemini provides accurate and informative content, making it a valuable resource for research and knowledge. The tool's multimodal capabilities allow it to process text, images, and other formats, expanding its applications across different industries. 

Gemini also demonstrates reasoning and problem-solving skills, potentially improving its capabilities through ongoing research and development. Users within the Google ecosystem can seamlessly integrate Gemini with other Google tools and services, streamlining their workflow.

Informative and accurate content generation

Multimodal capabilities across text, images, and other formats

Potential for continuous improvement and enhanced capabilities

Seamless integration with Google tools and services

Limited public access may restrict adoption and testing

Risk of inaccurate information

Inherited biases and creative limitations

4. Jasper AI: A Marketing Copywriting Whiz 

Jasper.ai is an AI writing tool that generates marketing copy for various purposes, such as blog posts, product descriptions, company bios, ad copy, and social media captions. With hundreds of templates, Jasper.ai simplifies content creation for marketers of all levels. 

The tool's ability to generate high-quality content quickly and efficiently is beneficial for companies looking to scale up their content production. Jasper.ai has several advantages, including natural-sounding content generation. However, it has limitations, such as a lack of personality and voice, the potential need for heavy editing, and struggles with niche topics.

Quick content generation within seconds

Natural-sounding, well-written, and accurate output

Sparks new ideas and angles for content creation

Affordable pricing for small businesses

Lack of personality and voice in content

May require heavy editing for specific content types

Struggles with niche topics and lacks fact-checking capabilities

5. Jenni AI: Your Personalized Writing Assistant 

Jenni AI is an AI-powered writing tool that assists students in generating ideas, optimizing their writing, and improving SEO. This tool provides personalized writing assistance, offers prompts, generates drafts, and aligns with chosen style guides to jumpstart the writing process. 

It also includes paraphrasing and rewriting support with an in-built plagiarism checker, allowing users to transform content quickly. While Jenni AI has numerous advantages, including personalized writing assistance and research integration, it also has limitations like reduced speed of content creation and limited content types and tone suggestions.

Personalized line-by-line writing assistance

Writing prompts and initial draft generation capabilities

Paraphrasing and rewriting support with plagiarism checker

Built-in research engine for content creation

Reduced speed of content creation

Limited content types and tone suggestions

Risk of meaning changes in paraphrasing

Limited translation support for non-native English speakers

6. Microsoft Bing AI: A Research Assistant Built into Your Search Engine 

Microsoft Bing AI is an AI-powered search functionality incorporating GPT-4 technology to deliver timely and relevant search results. This virtual assistant can understand complex prompts and provide advanced search features.

Access real-time information and offer rich media search options. Integrated with the Microsoft ecosystem, Bing AI enhances user workflows, leverages natural language processing and conversational search capabilities, and prioritizes user privacy and security. Despite its advantages, Bing AI may need help with its lower popularity than Google and potential variability in search accuracy and feature lag.

Tight integration with Microsoft products

Advanced search features and contextual understanding

Up-to-date information and real-time data access

Robust search options for various media types

Less popular than Google

Perception and familiarity challenges

Potential variability in search accuracy

Feature lag compared to competitors

7. DialoGPT: An AI Model for Human-like Conversations 

DialoGPT is an AI model tailored for human-like conversations and can engage in natural dialogues on diverse topics. This large-scale transformer model retains context over multiple conversational turns, handles various topics and conversational styles, and can be fine-tuned for specific applications or industries. 

DialoGPT users can integrate it into chatbots, customer service solutions, and virtual assistants to enhance user interactions. While DialoGPT has numerous advantages, such as contextual awareness and training on diverse data, it also faces challenges like response quality variability and maintaining coherence during more prolonged or complex conversations.

Context maintenance over multiple conversation turns

Trained on a large dataset of conversations

Customizable for specific applications or industries

Integration potential with various applications

Response quality variability

Context limitation in longer or complex conversations

Lack of real-world knowledge and potential biases

Inaccuracies in responses

8. Google's Bard AI: An AI Chatbot for Research 

Google's Bard AI is an experimental conversational AI service built on LaMDA technology. It offers AI-powered search and response functionality. This AI chatbot can answer user queries, access the latest information, and assist with tasks like restaurant reservations and flight bookings. 

Integrated with Google services, Bard AI benefits from Google's vast data resources to generate informative and contextually relevant answers. While Bard AI has several advantages, like integration with Google's ecosystem and rich contextual knowledge, it also faces challenges such as dependence on Google's data, privacy concerns, and response variability.

Integration with Google services and data resources

Rich contextual knowledge and informative responses

Natural solid language generation capabilities

Continuous updates and improvements through Google's ecosystem

Dependence on Google's data and potential biases

Privacy concerns regarding user data handling

Response variability and accuracy challenges

Limited personalization capabilities

• Literature Search Template • ChatGPT Prompts For Research • How To Find Gaps In Research • Research Journal Example • How To Find Limitations Of A Study • How To Do A Literature Search • Research Concept Map • Meta-Analysis Methods • How To Identify Bias In A Source • Search Strategies For Research • Literature Search Template • How To Read A Research Paper Quickly • How To Evaluate An Article • ChatGPT Summarize Paper • How To Take Notes For A Research Paper

What about Attribution and Originality?

Using ChatGPT for research papers brings about ethical considerations like attribution and originality. You must cite the source appropriately if you use information or ideas generated by ChatGPT. ChatGPT provides information based on patterns in the data on which it was trained. While it can help create ideas or provide explanations, the final research should reflect original analysis and not rely solely on AI-generated content. 

Is It Accurate? Do I Need to Verify Its Claims?

Accuracy and verification are also crucial when using AI tools like ChatGPT for research. While it can provide helpful information, verifying facts and cross-checking data from reliable sources is essential. ChatGPT responses should be used as a starting point or a supplementary resource, not as the basis for your research findings. 

Should I Be Transparent About My Use of AI?

Transparency is another critical consideration when using AI tools like ChatGPT for research. It is important to be transparent about your use of AI in your research. If ChatGPT or similar tools contributed significantly to your research process, acknowledging this in your methodology can enhance the credibility of your work. 

Does Using AI Tools Align With Academic Integrity?

Finally, ensure that using AI tools aligns with the academic integrity policies of your institution or the guidelines of the publication you’re submitting to. Some institutions may have specific rules about using AI in research.

1. The Problem With ChatGPT's Answers: They Can Be Biased

ChatGPT can generate some pretty convincing text, but it can also provide information that’s wrong, outdated, or biased. One of the main limitations is that ChatGPT’s data is from web scraping knowledge databases, social media, and open data sources. Many of these often derive from humans. Therefore, it can potentially pick up biased and sometimes prejudiced data. For instance, the AI system can include demographic, confirmation, and sampling biases.  

2. The Problem With ChatGPT's Understanding: It Lacks Context  

Speaking of bias, the AI model can’t understand specific contexts like humans can, such as sarcasm, humor, or irony. ChatGPT might not understand sarcasm and will give you a straightforward answer if you add sarcasm to a query.   

3. The Problem With ChatGPT's Writing: It Can Be Awkward  

ChatGPT sometimes writes in longer prose unless prompted otherwise. Its sensitivity to grammatical errors, typos, and misspellings is also limited. Even if there are no significant grammatical errors or misspellings, ChatGPT might write in passive voice rather than active. This AI’s writing style again brings up the need for human oversight.   

These limitations can easily be prevented by using an advanced tool like Otio. Let Otio be your AI research and writing partner — try Otio for free today !

Writing a research paper is a real challenge. First, you need to pick a topic and then narrow it down to something that will work for your assignment. Next, you must research what others have written about your topic. 

From there, you must organize your findings, formulate a thesis, and create an outline before writing the paper. Each of these steps can be daunting on their own, and together, they make the task of writing a research paper seem monumental. 

Let Otio be your AI research and writing partner — try Otio for free today !

• AI For Summarizing Research Papers • Literature Review Tools • How To Identify Theoretical Framework In An Article • Graduate School Reading • Research Tools • AI For Academic Research • Research Paper Organizer • Best AI Tools For Research • Zotero Alternatives • Zotero Vs Endnote • Mendeley Alternative • Literature Matrix Generator • Unriddle AI Alternatives • Sharly AI Alternatives • ChatGPT Literature Review

Aug 20, 2024

11 Best Mendeley Alternatives For Reference Management

Aug 19, 2024

How To Use ChatGPT For Literature Review In 8 Simple Steps

Join over 50,000 researchers changing the way they read & write

Chrome Extension

© 2024 Frontdoor Labs Ltd.

Terms of Service

Privacy Policy

Refund Policy

Join thousands of other scholars and researchers

Try Otio Free

© 2023 Frontdoor Labs Ltd.

Main Navigation Menu

Ai literacy in the age of chatgpt.

• Getting Started
• ChatGPT and pedagogy
• AI detection tools
• Citing generative AI
• Effective use of ChatGPT & other LLMs
• Fact-checking is always needed

Effective use of ChatGPT, Copilo, Gemini and other LLMs

What is chatgpt good for and not good for.

Remember,  you'll always need to verify the information,  because ChatGPT will sometimes make things ups (known as "hallucinations.") What is it good for?

• Brainstorming ideas
• Narrowing your topic ideas for a research paper, and keywords for searching in library databases. See  Generate Topics for Your Research Paper with ChatGPT.
• Explaining information in ways that are easy to understand
• Summarizing and outlining
• Asking questions  (be sure to fact check the results)  You can ask a million questions without fear of being judged.
• Translating text to different languages (not completely fluent in every language)
• Helping write or debug computing code

What is it not so good for?

• Perplexity AI    
• Microsoft Copilot  You may also want to try one of these  tools that combine generative AI with academic searching , in order to summarize and find more sources with semantic searching.  
• Asking for any information that would have dire consequences if it was incorrect (such as health, financial, legal advice, and so on). This is because of its tendency to sometimes make up answers, but still sound very confident.

What is prompting? Simply, it's what you type into the chat box.

The way you prompt makes a huge difference in the output that ChatGPT gives you. So it's worth learning some tips.

Always verify the information it gives you. Think of ChatGPT as your personal intern. They need very specific instructions, and they need you to verify the information.

ChatGPT sometimes makes things up.  That's because it's designed to write in a way that sounds like human writing. It's not designed to know facts.

Tips for writing effective prompts

• Give it some context or a role to play.
• Give it very detailed instructions, including how you would like the results formatted.
• Keep conversing and asking for changes. Ask it to revise the answer in various ways.
• A role could be, "Act as an expert in [fill in the blank]."  Act as an expert community organizer. Act as a high school biology teacher. Act as a comedian.  
• Example prompt: Act as an expert academic librarian. I’m writing a research paper for Sociology and I need help coming up with a topic. I’m interested in topics related to climate change. Please give me a list of 10 topic ideas related to climate change.  

I didn't like any of those topics. Please give me 10 more.

Learn more in this book (available online with your NetID).

Call Number: Available online with your UCM SSO.

Publication Date: 2024

This book offers strategies and practical guidance for crafting prompts. Includes tips and tricks, along with general concepts.

More tips for ChatGPT

• Sometimes it gets confused if you change topics in the middle of a conversation. When you want to  change the subject, start a new chat.  
• It will remember what you've said in the course of a conversation, so  you don't have to repeat everything again.  Just continue like you're talking to your intern.  
• Don't ask ChatGPT (free version) for a list of sources.  It will often make them up. Instead use library search, library databases, or Google Scholar. See   I can’t find the citations that ChatGPT gave me. What should I do?  
• Choose an output format.  In addition to paragraphs it can give you a table, a bulleted list, ascii art, multiple choice quiz questions, emojis, computer code, and more.  
• In ChatGPT  you can see a history of your conversations. You can go back to a previous conversation and continue it.  If you like, in the settings you can delete your history and turn off the saving of future history. You can also export your history and save it on your own computer.  
• Remember,  don't enter any personal, private data in ChatGPT , because OpenAI may use your input to help improve the model. The free version is a research experiment.  If you don't want your data used to help improve ChatGPT, you can turn it off in the settings. Go to your name, then Settings, then Data Controls and turn off, "Improve the model for everyone."
• << Previous: Citing generative AI
• Next: Fact-checking is always needed >>
• Last Updated: Aug 16, 2024 12:13 PM
• URL: https://guides.library.ucmo.edu/c.php?g=1417648

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• 18 January 2023

ChatGPT listed as author on research papers: many scientists disapprove

• Chris Stokel-Walker 0

Chris Stokel-Walker is a freelance journalist in Newcastle, UK.

You can also search for this author in PubMed   Google Scholar

The artificial-intelligence (AI) chatbot ChatGPT that has taken the world by storm has made its formal debut in the scientific literature — racking up at least four authorship credits on published papers and preprints.

Access options

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

185,98 € per year

only 3,65 € per issue

Rent or buy this article

Prices vary by article type

Prices may be subject to local taxes which are calculated during checkout

Nature 613 , 620-621 (2023)

doi: https://doi.org/10.1038/d41586-023-00107-z

Kung, T. H. et al. Preprint at medRxiv https://doi.org/10.1101/2022.12.19.22283643 (2022).

O’Connor, S. & ChatGPT Nurse Educ. Pract. 66 , 103537 (2023).

Article   PubMed   Google Scholar  

ChatGPT & Zhavoronkov, A. Oncoscience 9 , 82–84 (2022).

GPT, Osmanovic Thunström, A. & Steingrimsson, S. Preprint at HAL https://hal.science/hal-03701250 (2022).

Download references

Reprints and permissions

Related Articles

Are ChatGPT and AlphaCode going to replace programmers?

Can floating homes make coastal communities resilient to climate risks?

Comment 19 AUG 24

How I’m looking to medicine’s past to heal hurt and support peace in the Middle East

World View 15 AUG 24

Maxine Singer obituary: biologist who shaped genetic engineering and fought discrimination

Obituary 02 AUG 24

South Korean science on the global stage

Nature Index 21 AUG 24

How South Korea can build better gender diversity into research

The citation black market: schemes selling fake references alarm scientists

News 20 AUG 24

Principal Investigator Positions at the Institute for Regenerative Biology and Medicine, CIMR

Regenerative Biology and Medicine, including but not limited to disease immunology, ageing, biochemistry of extracellular matrix...

Beijing, China

The Chinese Institutes for Medical Research (CIMR), Beijing

Principal Investigator Positions at the Institute for Molecular and Cellular Therapy, CIMR, Beijing

We're looking for outstanding scientists at all ranks interested in developing novel therapeutics in all disease areas.

2024 Recruitment notice Shenzhen Institute of Synthetic Biology: Shenzhen, China

The wide-ranging expertise drawing from technical, engineering or science professions...

Shenzhen,China

Shenzhen Institute of Synthetic Biology

Qiushi Chair Professor

Distinguished scholars with notable achievements and extensive international influence.

Hangzhou, Zhejiang, China

Zhejiang University

ZJU 100 Young Professor

Promising young scholars who can independently establish and develop a research direction.

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

AI poses no existential threat to humanity – new study finds

Large language models like ChatGPT cannot learn independently or acquire new skills, meaning they pose no existential threat to humanity.

• Press release
• Published on Monday 12 August 2024
• Last updated on Tuesday 20 August 2024
• View more announcements in Communications

ChatGPT and other large language models (LLMs) cannot learn independently or acquire new skills, meaning they pose no existential threat to humanity, according to new research from the University of Bath and the Technical University of Darmstadt in Germany.

The study , published today as part of the proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) – the premier international conference in natural language processing – reveals that LLMs have a superficial ability to follow instructions and excel at proficiency in language, however, they have no potential to master new skills without explicit instruction. This means they remain inherently controllable, predictable and safe.

The research team concluded that LLMs – which are being trained on ever larger datasets – can continue to be deployed without safety concerns, though the technology can still be misused.

With growth, these models are likely to generate more sophisticated language and become better at following explicit and detailed prompts, but they are highly unlikely to gain complex reasoning skills.

“The prevailing narrative that this type of AI is a threat to humanity prevents the widespread adoption and development of these technologies, and also diverts attention from the genuine issues that require our focus,” said Dr Harish Tayyar Madabushi , computer scientist at the University of Bath and co-author of the new study on the ‘emergent abilities’ of LLMs.

The collaborative research team, led by Professor Iryna Gurevych at the Technical University of Darmstadt in Germany, ran experiments to test the ability of LLMs to complete tasks that models have never come across before – the so-called emergent abilities.

As an illustration, LLMs can answer questions about social situations without ever having been explicitly trained or programmed to do so. While previous research suggested this was a product of models ‘knowing’ about social situations, the researchers showed that it was in fact the result of models using a well-known ability of LLMs to complete tasks based on a few examples presented to them, known as `in-context learning’ (ICL).

Through thousands of experiments, the team demonstrated that a combination of LLMs ability to follow instructions (ICL), memory and linguistic proficiency can account for both the capabilities and limitations exhibited by LLMs.

Dr Tayyar Madabushi said: “The fear has been that as models get bigger and bigger, they will be able to solve new problems that we cannot currently predict, which poses the threat that these larger models might acquire hazardous abilities including reasoning and planning.

“This has triggered a lot of discussion – for instance, at the AI Safety Summit last year at Bletchley Park, for which we were asked for comment – but our study shows that the fear that a model will go away and do something completely unexpected, innovative and potentially dangerous is not valid.

“Concerns over the existential threat posed by LLMs are not restricted to non-experts and have been expressed by some of the top AI researchers across the world."

However, Dr Tayyar Madabushi maintains this fear is unfounded as the researchers' tests clearly demonstrated the absence of emergent complex reasoning abilities in LLMs.

“While it's important to address the existing potential for the misuse of AI, such as the creation of fake news and the heightened risk of fraud, it would be premature to enact regulations based on perceived existential threats,” he said.

“Importantly, what this means for end users is that relying on LLMs to interpret and perform complex tasks which require complex reasoning without explicit instruction is likely to be a mistake. Instead, users are likely to benefit from explicitly specifying what they require models to do and providing examples where possible for all but the simplest of tasks.”

Professor Gurevych added: "… our results do not mean that AI is not a threat at all. Rather, we show that the purported emergence of complex thinking skills associated with specific threats is not supported by evidence and that we can control the learning process of LLMs very well after all. Future research should therefore focus on other risks posed by the models, such as their potential to be used to generate fake news."

Dr Harish Tayyar Madabushi describes the pros, cons and limitations of LLMs.

Media enquiries

Vittoria D'Alessio [email protected] +44 (0)1225 383135

Media Centre