{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T01:25:13Z","timestamp":1777339513614,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":101,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T00:00:00Z","timestamp":1710720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"funder":[{"name":"Ministry of Science and ICT, Republic of Korea","award":["2021-0-01347"],"award-info":[{"award-number":["2021-0-01347"]}]},{"name":"Ministry of Science and ICT (MSIT), Republic of Korea","award":["2019-0-00075"],"award-info":[{"award-number":["2019-0-00075"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,18]]},"DOI":"10.1145\/3640543.3645148","type":"proceedings-article","created":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T18:23:12Z","timestamp":1712341392000},"page":"385-404","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":46,"title":["Understanding Users\u2019 Dissatisfaction with ChatGPT Responses: Types, Resolving Tactics, and the Effect of Knowledge Level"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9782-086X","authenticated-orcid":false,"given":"Yoonsu","family":"Kim","sequence":"first","affiliation":[{"name":"Graduate School of AI, KAIST, Korea, Republic of"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1317-9056","authenticated-orcid":false,"given":"Jueon","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University, Korea, Republic of"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0680-0856","authenticated-orcid":false,"given":"Seoyoung","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Computing, KAIST, Korea, Republic of"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8227-1143","authenticated-orcid":false,"given":"Jaehyuk","family":"Park","sequence":"additional","affiliation":[{"name":"School of Public Policy and Management, Korea Development Institute, Korea, Republic of"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6348-4127","authenticated-orcid":false,"given":"Juho","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Computing, KAIST, Korea, Republic of"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,4,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Accessed on 10\/06\/2023. LLM Jailbreak Study. https:\/\/sites.google.com\/view\/llm-jailbreak-study."},{"key":"e_1_3_2_1_2_1","unstructured":"Accessed on 10\/08\/2023. ChatGPT is a new AI chatbot that can answer questions and write essays. https:\/\/www.cnbc.com\/2022\/12\/13\/chatgpt-is-a-new-ai-chatbot-that-can-answer-questions-and-write-essays.html."},{"key":"e_1_3_2_1_3_1","unstructured":"Accessed on 10\/08\/2023. ChatGPT Masterclass: The Guide to AI & Prompt Engineering Udemy. https:\/\/www.udemy.com\/course\/chatgpt-ai-masterclass\/."},{"key":"e_1_3_2_1_4_1","unstructured":"Accessed on 10\/08\/2023. gpt-4-system-card.pdf. https:\/\/cdn.openai.com\/papers\/gpt-4-system-card.pdf."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462624"},{"key":"e_1_3_2_1_6_1","volume-title":"A review on language models as knowledge bases. arXiv preprint arXiv:2204.06031","author":"AlKhamissi Badr","year":"2022","unstructured":"Badr AlKhamissi, Millicent Li, Asli Celikyilmaz, Mona Diab, and Marjan Ghazvininejad. 2022. A review on language models as knowledge bases. arXiv preprint arXiv:2204.06031 (2022)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.xops.2023.100324"},{"key":"e_1_3_2_1_8_1","volume-title":"ChatGPT Usage and Limitations. (Dec","author":"Azaria Amos","year":"2022","unstructured":"Amos Azaria. 2022. ChatGPT Usage and Limitations. (Dec. 2022). https:\/\/hal.science\/hal-03913837 working paper or preprint."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Yejin Bang Samuel Cahyawijaya Nayeon Lee Wenliang Dai Dan Su Bryan Wilie Holy Lovenia Ziwei Ji Tiezheng Yu Willy Chung Quyet\u00a0V. Do Yan Xu and Pascale Fung. 2023. A Multitask Multilingual Multimodal Evaluation of ChatGPT on Reasoning Hallucination and Interactivity. arxiv:2302.04023\u00a0[cs.CL]","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1963405.1963424"},{"key":"e_1_3_2_1_11_1","volume-title":"Design Recommendations, and Open Challenges. arXiv preprint arXiv:2306.04765","author":"Behrooz Morteza","year":"2023","unstructured":"Morteza Behrooz, William Ngan, Joshua Lane, Giuliano Morse, Benjamin Babcock, Kurt Shuster, Mojtaba Komeili, Moya Chen, Melanie Kambadur, Y-Lan Boureau, 2023. The HCI Aspects of Public Deployment of Research Chatbots: A User Study, Design Recommendations, and Open Challenges. arXiv preprint arXiv:2306.04765 (2023)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_2_1_13_1","volume-title":"Can GPT-3 perform statutory reasoning?arXiv preprint arXiv:2302.06100","author":"Blair-Stanek Andrew","year":"2023","unstructured":"Andrew Blair-Stanek, Nils Holzenberger, and Benjamin Van\u00a0Durme. 2023. Can GPT-3 perform statutory reasoning?arXiv preprint arXiv:2302.06100 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"A categorical archive of chatgpt failures. arXiv preprint arXiv:2302.03494","author":"Borji Ali","year":"2023","unstructured":"Ali Borji. 2023. A categorical archive of chatgpt failures. arXiv preprint arXiv:2302.03494 (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534642"},{"key":"e_1_3_2_1_16_1","volume-title":"Psychology of learning and motivation. Vol.\u00a062","author":"Brown-Schmidt Sarah","unstructured":"Sarah Brown-Schmidt, Si\u00a0On Yoon, and Rachel\u00a0Anna Ryskin. 2015. People as contexts in conversation. In Psychology of learning and motivation. Vol.\u00a062. Elsevier, 59\u201399."},{"key":"e_1_3_2_1_17_1","volume-title":"Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712","author":"Bubeck S\u00e9bastien","year":"2023","unstructured":"S\u00e9bastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin\u00a0Tat Lee, Yuanzhi Li, Scott Lundberg, 2023. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"A comprehensive survey of ai-generated content (aigc): A history of generative ai from gan to chatgpt. arXiv preprint arXiv:2303.04226","author":"Cao Yihan","year":"2023","unstructured":"Yihan Cao, Siyu Li, Yixin Liu, Zhiling Yan, Yutong Dai, Philip\u00a0S Yu, and Lichao Sun. 2023. A comprehensive survey of ai-generated content (aigc): A history of generative ai from gan to chatgpt. arXiv preprint arXiv:2303.04226 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Deep reinforcement learning from human preferences. Advances in neural information processing systems 30","author":"Christiano F","year":"2017","unstructured":"Paul\u00a0F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_20_1","volume-title":"How to Prompt? Opportunities and Challenges of Zero-and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models. arXiv preprint arXiv:2209.01390","author":"Dang Hai","year":"2022","unstructured":"Hai Dang, Lukas Mecke, Florian Lehmann, Sven Goller, and Daniel Buschek. 2022. How to Prompt? Opportunities and Challenges of Zero-and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models. arXiv preprint arXiv:2209.01390 (2022)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3554727"},{"key":"e_1_3_2_1_22_1","volume-title":"Analysis of large-language model versus human performance for genetics questions. European Journal of Human Genetics","author":"Duong Dat","year":"2023","unstructured":"Dat Duong and Benjamin\u00a0D Solomon. 2023. Analysis of large-language model versus human performance for genetics questions. European Journal of Human Genetics (2023), 1\u20133."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2023.102642"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00410"},{"key":"e_1_3_2_1_25_1","volume-title":"A SWOT analysis of ChatGPT: Implications for educational practice and research. Innovations in Education and Teaching International","author":"Farrokhnia Mohammadreza","year":"2023","unstructured":"Mohammadreza Farrokhnia, Seyyed\u00a0Kazem Banihashem, Omid Noroozi, and Arjen Wals. 2023. A SWOT analysis of ChatGPT: Implications for educational practice and research. Innovations in Education and Teaching International (2023), 1\u201315."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13347-023-00621-y"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3593989"},{"key":"e_1_3_2_1_28_1","volume-title":"Realtoxicityprompts: Evaluating neural toxic degeneration in language models. arXiv preprint arXiv:2009.11462","author":"Gehman Samuel","year":"2020","unstructured":"Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah\u00a0A Smith. 2020. Realtoxicityprompts: Evaluating neural toxic degeneration in language models. arXiv preprint arXiv:2009.11462 (2020)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.05.004"},{"key":"e_1_3_2_1_30_1","unstructured":"Biyang Guo Xin Zhang Ziyuan Wang Minqi Jiang Jinran Nie Yuxuan Ding Jianwei Yue and Yupeng Wu. 2023. How Close is ChatGPT to Human Experts? Comparison Corpus Evaluation and Detection. arxiv:2301.07597\u00a0[cs.CL]"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3300381"},{"key":"e_1_3_2_1_32_1","volume-title":"Challenges, Limitations, and Practical Usage. TechRxiv","author":"Hadi Muhammad\u00a0Usman","year":"2023","unstructured":"Muhammad\u00a0Usman Hadi, R Qureshi, A Shah, M Irfan, A Zafar, MB Shaikh, N Akhtar, J Wu, and S Mirjalili. 2023. A Survey on Large Language Models: Applications, Challenges, Limitations, and Practical Usage. TechRxiv (2023)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1177\/1088868307309605"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.nbt.2023.02.001"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1526709.1526773"},{"key":"e_1_3_2_1_36_1","volume-title":"Towards reasoning in large language models: A survey. arXiv preprint arXiv:2212.10403","author":"Huang Jie","year":"2022","unstructured":"Jie Huang and Kevin Chen-Chuan Chang. 2022. Towards reasoning in large language models: A survey. arXiv preprint arXiv:2212.10403 (2022)."},{"key":"e_1_3_2_1_37_1","volume-title":"BECEL: Benchmark for Consistency Evaluation of Language Models. In International Conference on Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:252819451","author":"Jang Myeongjun","year":"2022","unstructured":"Myeongjun Jang, Deuk\u00a0Sin Kwon, and Thomas Lukasiewicz. 2022. BECEL: Benchmark for Consistency Evaluation of Language Models. In International Conference on Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:252819451"},{"key":"e_1_3_2_1_38_1","volume-title":"Consistency analysis of chatgpt. arXiv preprint arXiv:2303.06273","author":"Jang Myeongjun","year":"2023","unstructured":"Myeongjun Jang and Thomas Lukasiewicz. 2023. Consistency analysis of chatgpt. arXiv preprint arXiv:2303.06273 (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_1_40_1","volume-title":"Can Large Language Models Infer Causation from Correlation?arXiv preprint arXiv:2306.05836","author":"Jin Zhijing","year":"2023","unstructured":"Zhijing Jin, Jiarui Liu, Zhiheng Lyu, Spencer Poff, Mrinmaya Sachan, Rada Mihalcea, Mona Diab, and Bernhard Scholkopf. 2023. Can Large Language Models Infer Causation from Correlation?arXiv preprint arXiv:2306.05836 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Ishika Joshi Ritvik Budhiraja Harshal Dev Jahnvi Kadia M.\u00a0Osama Ataullah Sayan Mitra Dhruv Kumar and Harshal\u00a0D. Akolekar. 2023. ChatGPT in the Classroom: An Analysis of Its Strengths and Weaknesses for Solving Undergraduate Computer Science Questions. https:\/\/api.semanticscholar.org\/CorpusID:258417916","DOI":"10.1145\/3626252.3630803"},{"key":"e_1_3_2_1_42_1","unstructured":"Jean Kaddour Joshua Harris Maximilian Mozes Herbie Bradley Roberta Raileanu and Robert McHardy. 2023. Challenges and Applications of Large Language Models. arxiv:2307.10169\u00a0[cs.CL]"},{"key":"e_1_3_2_1_43_1","volume-title":"ChatGPT for good? On opportunities and challenges of large language models for education. Learning and individual differences 103","author":"Kasneci Enkelejda","year":"2023","unstructured":"Enkelejda Kasneci, Kathrin Se\u00dfler, Stefan Kuchemann, Maria Bannert, Daryna Dementieva, Frank Fischer, Urs Gasser, Georg Groh, Stephan Gunnemann, Eyke Hullermeier, 2023. ChatGPT for good? On opportunities and challenges of large language models for education. Learning and individual differences 103 (2023), 102274."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.12669\/pjms.39.2.7653"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Felipe\u00a0C Kitamura. 2023. ChatGPT is shaping the future of medical writing but still requires human judgment. e230171\u00a0pages.","DOI":"10.1148\/radiol.230171"},{"key":"e_1_3_2_1_46_1","volume-title":"Large language models are zero-shot reasoners. Advances in neural information processing systems 35","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang\u00a0Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems 35 (2022), 22199\u201322213."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5530\/bems.9.1.5"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2023.02.003"},{"key":"e_1_3_2_1_49_1","volume-title":"Evaluating the logical reasoning ability of chatgpt and gpt-4. arXiv preprint arXiv:2304.03439","author":"Liu Hanmeng","year":"2023","unstructured":"Hanmeng Liu, Ruoxi Ning, Zhiyang Teng, Jian Liu, Qiji Zhou, and Yue Zhang. 2023. Evaluating the logical reasoning ability of chatgpt and gpt-4. arXiv preprint arXiv:2304.03439 (2023)."},{"key":"e_1_3_2_1_50_1","unstructured":"Yi Liu Gelei Deng Zhengzi Xu Yuekang Li Yaowen Zheng Ying Zhang Lida Zhao Tianwei Zhang and Yang Liu. 2023. Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study. arxiv:2305.13860\u00a0[cs.SE]"},{"key":"e_1_3_2_1_51_1","unstructured":"Yang Liu Yuanshun Yao Jean-Francois Ton Xiaoying Zhang Ruocheng Guo Hao Cheng Yegor Klochkov Muhammad\u00a0Faaiz Taufiq and Hang Li. 2023. Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models\u2019 Alignment. arxiv:2308.05374\u00a0[cs.AI]"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.nuse-1.5"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858288"},{"key":"e_1_3_2_1_54_1","volume-title":"Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651","author":"Madaan Aman","year":"2023","unstructured":"Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, 2023. Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651 (2023)."},{"key":"e_1_3_2_1_55_1","volume-title":"Language models of code are few-shot commonsense learners. arXiv preprint arXiv:2210.07128","author":"Madaan Aman","year":"2022","unstructured":"Aman Madaan, Shuyan Zhou, Uri Alon, Yiming Yang, and Graham Neubig. 2022. Language models of code are few-shot commonsense learners. arXiv preprint arXiv:2210.07128 (2022)."},{"key":"e_1_3_2_1_56_1","volume-title":"Artificial intelligence discusses the role of artificial intelligence in translational medicine: a JACC: basic to translational science interview with ChatGPT. Basic to Translational Science 8, 2","author":"Mann L","year":"2023","unstructured":"Douglas\u00a0L Mann. 2023. Artificial intelligence discusses the role of artificial intelligence in translational medicine: a JACC: basic to translational science interview with ChatGPT. Basic to Translational Science 8, 2 (2023), 221\u2013223."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173580"},{"key":"e_1_3_2_1_59_1","unstructured":"Roberto Navigli Simone Conia and Bjorn Ross. [n. d.]. Biases in Large Language Models: Origins Inventory and Discussion. ACM Journal of Data and Information Quality ([n. d.])."},{"key":"e_1_3_2_1_60_1","first-page":"309","article-title":"Law informs code: A legal informatics approach to aligning artificial intelligence with humans","volume":"20","author":"Nay J","year":"2022","unstructured":"John\u00a0J Nay. 2022. Law informs code: A legal informatics approach to aligning artificial intelligence with humans. Nw. J. Tech. & Intell. Prop. 20 (2022), 309.","journal-title":"Nw. J. Tech. & Intell. Prop."},{"key":"e_1_3_2_1_61_1","volume-title":"Is ChatGPT a Good Tool for T&CM Students in Studying Pharmacology?Available at SSRN 4324310","author":"Nisar Saima","year":"2023","unstructured":"Saima Nisar and Muhammad\u00a0Shahzad Aslam. 2023. Is ChatGPT a Good Tool for T&CM Students in Studying Pharmacology?Available at SSRN 4324310 (2023)."},{"key":"e_1_3_2_1_62_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arxiv:2303.08774\u00a0[cs.CL]"},{"key":"e_1_3_2_1_63_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730\u201327744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"crossref","unstructured":"Ethan Perez Sam Ringer Kamil\u0117 Luko\u0161i\u016bt\u0117 Karina Nguyen Edwin Chen Scott Heiner Craig Pettit Catherine Olsson Sandipan Kundu Saurav Kadavath Andy Jones Anna Chen Ben Mann Brian Israel Bryan Seethor Cameron McKinnon Christopher Olah Da Yan Daniela Amodei Dario Amodei Dawn Drain Dustin Li Eli Tran-Johnson Guro Khundadze Jackson Kernion James Landis Jamie Kerr Jared Mueller Jeeyoon Hyun Joshua Landau Kamal Ndousse Landon Goldberg Liane Lovitt Martin Lucas Michael Sellitto Miranda Zhang Neerav Kingsland Nelson Elhage Nicholas Joseph Noem\u00ed Mercado Nova DasSarma Oliver Rausch Robin Larson Sam McCandlish Scott Johnston Shauna Kravec Sheer\u00a0El Showk Tamera Lanham Timothy Telleen-Lawton Tom Brown Tom Henighan Tristan Hume Yuntao Bai Zac Hatfield-Dodds Jack Clark Samuel\u00a0R. Bowman Amanda Askell Roger Grosse Danny Hernandez Deep Ganguli Evan Hubinger Nicholas Schiefer and Jared Kaplan. 2022. Discovering Language Model Behaviors with Model-Written Evaluations. arxiv:2212.09251\u00a0[cs.CL]","DOI":"10.18653\/v1\/2023.findings-acl.847"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174214"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/EDUCON54358.2023.10125121"},{"key":"e_1_3_2_1_67_1","volume-title":"Limitations of language models in arithmetic and symbolic induction. arXiv preprint arXiv:2208.05051","author":"Qian Jing","year":"2022","unstructured":"Jing Qian, Hong Wang, Zekun Li, Shiyang Li, and Xifeng Yan. 2022. Limitations of language models in arithmetic and symbolic induction. arXiv preprint arXiv:2208.05051 (2022)."},{"key":"e_1_3_2_1_68_1","volume-title":"Is ChatGPT a general-purpose natural language processing task solver?arXiv preprint arXiv:2302.06476","author":"Qin Chengwei","year":"2023","unstructured":"Chengwei Qin, Aston Zhang, Zhuosheng Zhang, Jiaao Chen, Michihiro Yasunaga, and Diyi Yang. 2023. Is ChatGPT a general-purpose natural language processing task solver?arXiv preprint arXiv:2302.06476 (2023)."},{"key":"e_1_3_2_1_69_1","volume-title":"ChatGPT for Education and Research: Opportunities, Threats, and Strategies. Applied Sciences","author":"Rahman Mostafizer","year":"2023","unstructured":"Md.\u00a0Mostafizer Rahman and Yutaka Watanobe. 2023. ChatGPT for Education and Research: Opportunities, Threats, and Strategies. Applied Sciences (2023). https:\/\/api.semanticscholar.org\/CorpusID:258584102"},{"key":"e_1_3_2_1_70_1","volume-title":"Evaluating ChatGPT as an adjunct for radiologic decision-making. medRxiv","author":"Rao A","year":"2023","unstructured":"A Rao, J Kim, M Kamineni, M Pang, W Lie, and MD Succi. 2023. Evaluating ChatGPT as an adjunct for radiologic decision-making. medRxiv, 2023-02."},{"key":"e_1_3_2_1_71_1","volume-title":"ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet of Things and Cyber-Physical Systems","author":"Ray Partha\u00a0Pratim","year":"2023","unstructured":"Partha\u00a0Pratim Ray. 2023. ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet of Things and Cyber-Physical Systems (2023)."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451760"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2005.05.005"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"crossref","unstructured":"Malik Sallam. 2023. ChatGPT utility in healthcare education research and practice: systematic review on the promising perspectives and valid concerns. In Healthcare Vol.\u00a011. MDPI 887.","DOI":"10.3390\/healthcare11060887"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"crossref","unstructured":"Gaurav Sharma and Abhishek Thakur. 2023. ChatGPT in drug discovery. (2023).","DOI":"10.26434\/chemrxiv-2023-qgs3k"},{"key":"e_1_3_2_1_76_1","volume-title":"Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations. arXiv preprint arXiv:2305.13299","author":"Si Chenglei","year":"2023","unstructured":"Chenglei Si, Dan Friedman, Nitish Joshi, Shi Feng, Danqi Chen, and He He. 2023. Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations. arXiv preprint arXiv:2305.13299 (2023)."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.17011\/ht\/urn.201902201607"},{"key":"e_1_3_2_1_78_1","unstructured":"Anselm Strauss and Juliet Corbin. 1998. Basics of qualitative research techniques. (1998)."},{"key":"e_1_3_2_1_79_1","volume-title":"Kabilan Elangovan, Laura Gutierrez, Ting\u00a0Fang Tan, and Daniel Shu\u00a0Wei Ting.","author":"Thirunavukarasu Arun\u00a0James","year":"2023","unstructured":"Arun\u00a0James Thirunavukarasu, Darren Shu\u00a0Jeng Ting, Kabilan Elangovan, Laura Gutierrez, Ting\u00a0Fang Tan, and Daniel Shu\u00a0Wei Ting. 2023. Large language models in medicine. Nature medicine (2023), 1\u201311."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"crossref","unstructured":"H\u00a0Holden Thorp. 2023. ChatGPT is fun but not an author. 313\u2013313\u00a0pages.","DOI":"10.1126\/science.adg7879"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"crossref","unstructured":"Shubo Tian Qiao Jin Lana Yeganova Po-Ting Lai Qingqing Zhu Xiuying Chen Yifan Yang Qingyu Chen Won Kim Donald\u00a0C. Comeau Rezarta Islamaj Aadit Kapoor Xin Gao and Zhiyong Lu. 2023. Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health. arxiv:2306.10070\u00a0[cs.CY]","DOI":"10.1093\/bib\/bbad493"},{"key":"e_1_3_2_1_82_1","unstructured":"Teun\u00a0A Van\u00a0Dijk. 2007. Comments on context and conversation. Citeseer."},{"key":"e_1_3_2_1_83_1","volume-title":"Can ChatGPT write a good boolean query for systematic review literature search?arXiv preprint arXiv:2302.03495","author":"Wang Shuai","year":"2023","unstructured":"Shuai Wang, Harrisen Scells, Bevan Koopman, and Guido Zuccon. 2023. Can ChatGPT write a good boolean query for systematic review literature search?arXiv preprint arXiv:2302.03495 (2023)."},{"key":"e_1_3_2_1_84_1","volume-title":"Aakanksha Chowdhery, and Denny Zhou.","author":"Wang Xuezhi","year":"2022","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)."},{"key":"e_1_3_2_1_85_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc\u00a0V Le, Denny Zhou, 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824\u201324837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_86_1","volume-title":"Ethical and social risks of harm from language models. arXiv preprint arXiv:2112.04359","author":"Weidinger Laura","year":"2021","unstructured":"Laura Weidinger, John Mellor, Maribeth Rauh, Conor Griffin, Jonathan Uesato, Po-Sen Huang, Myra Cheng, Mia Glaese, Borja Balle, Atoosa Kasirzadeh, 2021. Ethical and social risks of harm from language models. arXiv preprint arXiv:2112.04359 (2021)."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533088"},{"key":"e_1_3_2_1_88_1","volume-title":"A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382","author":"White Jules","year":"2023","unstructured":"Jules White, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, and Douglas\u00a0C Schmidt. 2023. A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382 (2023)."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534136"},{"key":"e_1_3_2_1_90_1","unstructured":"Xianjun Yang Yan Li Xinlu Zhang Haifeng Chen and Wei Cheng. 2023. Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization. arxiv:2302.08081\u00a0[cs.CL]"},{"key":"e_1_3_2_1_91_1","volume-title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models. ArXiv abs\/2309.06794","author":"Ye Hongbin","year":"2023","unstructured":"Hongbin Ye, Tong Liu, Aijia Zhang, Wei Hua, and Weiqiang Jia. 2023. Cognitive Mirage: A Review of Hallucinations in Large Language Models. ArXiv abs\/2309.06794 (2023). https:\/\/api.semanticscholar.org\/CorpusID:261705916"},{"key":"e_1_3_2_1_92_1","volume-title":"Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma. medRxiv","author":"Yeo Yee\u00a0Hui","year":"2023","unstructured":"Yee\u00a0Hui Yeo, Jamil\u00a0S Samaan, Wee\u00a0Han Ng, Peng-Sheng Ting, Hirsh Trivedi, Aarshi Vipani, Walid Ayoub, Ju\u00a0Dong Yang, Omer Liran, Brennan Spiegel, 2023. Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma. medRxiv (2023), 2023\u201302."},{"key":"e_1_3_2_1_93_1","volume-title":"How well do Large Language Models perform in Arithmetic tasks?arXiv preprint arXiv:2304.02015","author":"Yuan Zheng","year":"2023","unstructured":"Zheng Yuan, Hongyi Yuan, Chuanqi Tan, Wei Wang, and Songfang Huang. 2023. How well do Large Language Models perform in Arithmetic tasks?arXiv preprint arXiv:2304.02015 (2023)."},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"key":"e_1_3_2_1_95_1","unstructured":"Chaoning Zhang Chenshuang Zhang Chenghao Li Yu Qiao Sheng Zheng Sumit\u00a0Kumar Dam Mengchun Zhang Jung\u00a0Uk Kim Seong\u00a0Tae Kim Jinwoo Choi Gyeong-Moon Park Sung-Ho Bae Lik-Hang Lee Pan Hui In\u00a0So Kweon and Choong\u00a0Seon Hong. 2023. One Small Step for Generative AI One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era. arxiv:2304.06488\u00a0[cs.CY]"},{"key":"e_1_3_2_1_96_1","volume-title":"Automatic chain of thought prompting in large language models. arXiv preprint arXiv:2210.03493","author":"Zhang Zhuosheng","year":"2022","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. 2022. Automatic chain of thought prompting in large language models. arXiv preprint arXiv:2210.03493 (2022)."},{"key":"e_1_3_2_1_97_1","unstructured":"Wayne\u00a0Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong Yifan Du Chen Yang Yushuo Chen Zhipeng Chen Jinhao Jiang Ruiyang Ren Yifan Li Xinyu Tang Zikang Liu Peiyu Liu Jian-Yun Nie and Ji-Rong Wen. 2023. A Survey of Large Language Models. arxiv:2303.18223\u00a0[cs.CL]"},{"key":"e_1_3_2_1_98_1","unstructured":"Shen Zheng Jie Huang and Kevin Chen-Chuan Chang. 2023. Why Does ChatGPT Fall Short in Providing Truthful Answers?https:\/\/api.semanticscholar.org\/CorpusID:258865162"},{"key":"e_1_3_2_1_99_1","volume-title":"Navigating the grey area: Expressions of overconfidence and uncertainty in language models. arXiv preprint arXiv:2302.13439","author":"Zhou Kaitlyn","year":"2023","unstructured":"Kaitlyn Zhou, Dan Jurafsky, and Tatsunori Hashimoto. 2023. Navigating the grey area: Expressions of overconfidence and uncertainty in language models. arXiv preprint arXiv:2302.13439 (2023)."},{"key":"e_1_3_2_1_100_1","volume-title":"Large language models are human-level prompt engineers. arXiv preprint arXiv:2211.01910","author":"Zhou Yongchao","year":"2022","unstructured":"Yongchao Zhou, Andrei\u00a0Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. 2022. Large language models are human-level prompt engineers. arXiv preprint arXiv:2211.01910 (2022)."},{"key":"e_1_3_2_1_101_1","volume-title":"Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593","author":"Ziegler M","year":"2019","unstructured":"Daniel\u00a0M Ziegler, Nisan Stiennon, Jeffrey Wu, Tom\u00a0B Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving. 2019. Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593 (2019)."}],"event":{"name":"IUI '24: 29th International Conference on Intelligent User Interfaces","location":"Greenville SC USA","acronym":"IUI '24","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 29th International Conference on Intelligent User Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640543.3645148","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640543.3645148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:56:03Z","timestamp":1764550563000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640543.3645148"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,18]]},"references-count":101,"alternative-id":["10.1145\/3640543.3645148","10.1145\/3640543"],"URL":"https:\/\/doi.org\/10.1145\/3640543.3645148","relation":{},"subject":[],"published":{"date-parts":[[2024,3,18]]},"assertion":[{"value":"2024-04-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}