{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T14:21:47Z","timestamp":1779200507681,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":77,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Ministry of Science and ICT, Republic of Korea","award":["2021-0-01347"],"award-info":[{"award-number":["2021-0-01347"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,3]]},"DOI":"10.1145\/3630106.3662681","type":"proceedings-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T13:14:21Z","timestamp":1717593261000},"page":"2518-2531","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["One vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7491-986X","authenticated-orcid":false,"given":"Yoonjoo","family":"Lee","sequence":"first","affiliation":[{"name":"KAIST, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7224-2947","authenticated-orcid":false,"given":"Kihoon","family":"Son","sequence":"additional","affiliation":[{"name":"KAIST, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9078-6032","authenticated-orcid":false,"given":"Tae Soo","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5566-0877","authenticated-orcid":false,"given":"Jisu","family":"Kim","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8492-2525","authenticated-orcid":false,"given":"John Joon Young","family":"Chung","sequence":"additional","affiliation":[{"name":"Midjourney, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1911-836X","authenticated-orcid":false,"given":"Eytan","family":"Adar","sequence":"additional","affiliation":[{"name":"University of Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6348-4127","authenticated-orcid":false,"given":"Juho","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Retrieved","author":"Khan Academy","year":"2023","unstructured":"Khan Academy. 2023. Khanmigo: Khan Academy\u2019s AI-powered teaching assistant. Retrieved January 21, 2024 from https:\/\/blog.khanacademy.org\/teacher-khanmigo"},{"key":"e_1_3_2_1_2_1","volume-title":"Concrete Problems in AI Safety. ArXiv abs\/1606.06565","author":"Amodei Dario","year":"2016","unstructured":"Dario Amodei, Christopher Olah, Jacob Steinhardt, Paul\u00a0Francis Christiano, John Schulman, and Dandelion Man\u00e9. 2016. Concrete Problems in AI Safety. ArXiv abs\/1606.06565 (2016). https:\/\/api.semanticscholar.org\/CorpusID:10242377"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Stavros Antifakos Adrian Schwaninger and Bernt Schiele. 2004. Evaluating the Effects of Displaying Uncertainty in Context-Aware Applications. In Ubiquitous Computing. https:\/\/api.semanticscholar.org\/CorpusID:2342122","DOI":"10.1007\/978-3-540-30119-6_4"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Akari Asai and Hannaneh Hajishirzi. 2020. Logic-Guided Data Augmentation and Regularization for Consistent Question Answering. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:216035859","DOI":"10.18653\/v1\/2020.acl-main.499"},{"key":"e_1_3_2_1_5_1","volume-title":"Updates in Human-AI Teams: Understanding and Addressing the Performance\/Compatibility Tradeoff. In AAAI Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:53997192","author":"Bansal Gagan","year":"2019","unstructured":"Gagan Bansal, Besmira Nushi, Ece Kamar, Daniel\u00a0S. Weld, Walter\u00a0S. Lasecki, and Eric Horvitz. 2019. Updates in Human-AI Teams: Understanding and Addressing the Performance\/Compatibility Tradeoff. In AAAI Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:53997192"},{"key":"e_1_3_2_1_6_1","unstructured":"Edward Beeching Cl\u00e9mentine Fourrier Nathan Habib Sheon Han Nathan Lambert Nazneen Rajani Omar Sanseviero Lewis Tunstall and Thomas Wolf. 2023. Open LLM Leaderboard. https:\/\/huggingface.co\/spaces\/HuggingFaceH4\/open_llm_leaderboard."},{"key":"e_1_3_2_1_7_1","volume-title":"Making things hard on yourself, but in a good way: Creating desirable difficulties to enhance learning. Psychology and the real world: Essays illustrating fundamental contributions to society 2, 59-68","author":"Bjork L","year":"2011","unstructured":"Elizabeth\u00a0L Bjork, Robert\u00a0A Bjork, 2011. Making things hard on yourself, but in a good way: Creating desirable difficulties to enhance learning. Psychology and the real world: Essays illustrating fundamental contributions to society 2, 59-68 (2011)."},{"key":"e_1_3_2_1_8_1","unstructured":"Richard\u00a0E. Boyatzis. 1998. Transforming Qualitative Information: Thematic Analysis and Code Development."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449287"},{"key":"e_1_3_2_1_10_1","volume-title":"Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:203905467","author":"Camburu Oana-Maria","year":"2019","unstructured":"Oana-Maria Camburu, Brendan Shillingford, Pasquale Minervini, Thomas Lukasiewicz, and Phil Blunsom. 2019. Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:203905467"},{"key":"e_1_3_2_1_11_1","volume-title":"RELIC: Investigating Large Language Model Responses using Self-Consistency. ArXiv abs\/2311.16842","author":"Cheng Furui","year":"2023","unstructured":"Furui Cheng, Vil\u00e9m Zouhar, Simran Arora, Mrinmaya Sachan, Hendrik Strobelt, and Mennatallah El-Assady. 2023. RELIC: Investigating Large Language Model Responses using Self-Consistency. ArXiv abs\/2311.16842 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265466244"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300789"},{"key":"e_1_3_2_1_13_1","volume-title":"Investigating the Impact of User Trust on the Adoption and Use of ChatGPT: Survey Analysis. Journal of Medical Internet Research 25","author":"Choudhury Avishek","year":"2023","unstructured":"Avishek Choudhury and Hamid Shamszare. 2023. Investigating the Impact of User Trust on the Adoption and Use of ChatGPT: Survey Analysis. Journal of Medical Internet Research 25 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258922988"},{"key":"e_1_3_2_1_14_1","volume-title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge. ArXiv abs\/1803.05457","author":"Clark Peter","year":"2018","unstructured":"Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. 2018. Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge. ArXiv abs\/1803.05457 (2018). https:\/\/api.semanticscholar.org\/CorpusID:3922816"},{"key":"e_1_3_2_1_15_1","volume-title":"Conference on Empirical Methods in Natural Language Processing. https:\/\/api.semanticscholar.org\/CorpusID:258833288","author":"Cohen Roi","year":"2023","unstructured":"Roi Cohen, May Hamri, Mor Geva, and Amir Globerson. 2023. LM vs LM: Detecting Factual Errors via Cross Examination. In Conference on Empirical Methods in Natural Language Processing. https:\/\/api.semanticscholar.org\/CorpusID:258833288"},{"key":"e_1_3_2_1_16_1","volume-title":"Grounded theory.Medsurg nursing : official journal of the Academy of Medical-Surgical Nurses 22 2","author":"Connelly M.","year":"2013","unstructured":"Lynne\u00a0M. Connelly. 2013. Grounded theory.Medsurg nursing : official journal of the Academy of Medical-Surgical Nurses 22 2 (2013), 124, 127."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"David Dearman Alex Varshavsky Eyal de Lara and Khai\u00a0Nhut Truong. 2007. An Exploration of Location Error Estimation. In Ubiquitous Computing. https:\/\/api.semanticscholar.org\/CorpusID:9535527","DOI":"10.1007\/978-3-540-74853-3_11"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Pierre Dragicevic. 2016. Fair Statistical Communication in HCI. https:\/\/api.semanticscholar.org\/CorpusID:64470036","DOI":"10.1007\/978-3-319-26633-6_13"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00410"},{"key":"e_1_3_2_1_20_1","volume-title":"North American","author":"Fabbri R.","year":"1866","unstructured":"Alexander\u00a0R. Fabbri, Chien\u00a0Sheng Wu, Wenhao Liu, and Caiming Xiong. 2021. QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization. In North American Chapter of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:245218667"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533193"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511138"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Arthur\u00a0C. Graesser and Natalie\u00a0K. Person. 1994. Question Asking During Tutoring. https:\/\/api.semanticscholar.org\/CorpusID:15485207","DOI":"10.2307\/1163269"},{"key":"e_1_3_2_1_24_1","volume-title":"Measuring Massive Multitask Language Understanding. ArXiv abs\/2009.03300","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn\u00a0Xiaodong Song, and Jacob Steinhardt. 2020. Measuring Massive Multitask Language Understanding. ArXiv abs\/2009.03300 (2020). https:\/\/api.semanticscholar.org\/CorpusID:221516475"},{"key":"e_1_3_2_1_25_1","volume-title":"Unsolved Problems in ML Safety. ArXiv abs\/2109.13916","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Nicholas Carlini, John Schulman, and Jacob Steinhardt. 2021. Unsolved Problems in ML Safety. ArXiv abs\/2109.13916 (2021). https:\/\/api.semanticscholar.org\/CorpusID:238198240"},{"key":"e_1_3_2_1_26_1","volume-title":"Taxonomy, Challenges, and Open Questions. ArXiv abs\/2311.05232","author":"Huang Lei","year":"2023","unstructured":"Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2023. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions. ArXiv abs\/2311.05232 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265067168"},{"key":"e_1_3_2_1_27_1","volume-title":"yet inconsistent? Consistency Analysis on Language Understanding Models. ArXiv abs\/2108.06665","author":"Jang Myeongjun","year":"2021","unstructured":"Myeongjun Jang, Deuk\u00a0Sin Kwon, and Thomas Lukasiewicz. 2021. Accurate, yet inconsistent? Consistency Analysis on Language Understanding Models. ArXiv abs\/2108.06665 (2021). https:\/\/api.semanticscholar.org\/CorpusID:237091303"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_1_29_1","volume-title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension. ArXiv abs\/1705.03551","author":"Joshi Mandar","year":"2017","unstructured":"Mandar Joshi, Eunsol Choi, Daniel\u00a0S. Weld, and Luke Zettlemoyer. 2017. TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension. ArXiv abs\/1705.03551 (2017). https:\/\/api.semanticscholar.org\/CorpusID:26501419"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2010.03.008"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3415234"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3593978"},{"key":"e_1_3_2_1_33_1","volume-title":"Challenges and Opportunities of Moderating Usage of Large Language Models in Education. ArXiv abs\/2312.14969","author":"Krupp Lars","year":"2023","unstructured":"Lars Krupp, Steffen Steinert, Maximilian Kiefer-Emmanouilidis, Karina\u00a0E. Avila, Paul Lukowicz, Jochen Kuhn, Stefan K\u00fcchemann, and Jakob Karolus. 2023. Challenges and Opportunities of Moderating Usage of Large Language Models in Education. ArXiv abs\/2312.14969 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266550959"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1162\/tacl_a_00453","article-title":"SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization","volume":"10","author":"Laban Philippe","year":"2021","unstructured":"Philippe Laban, Tobias Schnabel, Paul\u00a0N. Bennett, and Marti\u00a0A. Hearst. 2021. SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization. Transactions of the Association for Computational Linguistics 10 (2021), 163\u2013177. https:\/\/api.semanticscholar.org\/CorpusID:244345901","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594087"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287590"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939874"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2004.832819"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581369"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603555.3603565"},{"key":"e_1_3_2_1_42_1","unstructured":"Junyi Li Jie Chen Ruiyang Ren Xiaoxue Cheng Wayne\u00a0Xin Zhao Jian-Yun Nie and Ji-Rong Wen. 2024. The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models. https:\/\/api.semanticscholar.org\/CorpusID:266844012"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1519023"},{"key":"e_1_3_2_1_44_1","volume-title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:237532606","author":"Lin C.","year":"2021","unstructured":"Stephanie\u00a0C. Lin, Jacob Hilton, and Owain Evans. 2021. TruthfulQA: Measuring How Models Mimic Human Falsehoods. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:237532606"},{"key":"e_1_3_2_1_45_1","volume-title":"Teaching Models to Express Their Uncertainty in Words. Trans. Mach. Learn. Res. 2022","author":"Lin C.","year":"2022","unstructured":"Stephanie\u00a0C. Lin, Jacob Hilton, and Owain Evans. 2022. Teaching Models to Express Their Uncertainty in Words. Trans. Mach. Learn. Res. 2022 (2022). https:\/\/api.semanticscholar.org\/CorpusID:249191391"},{"key":"e_1_3_2_1_46_1","volume-title":"Systematic and nonsystematic processing of majority and minority persuasive communications.Journal of Personality and Social Psychology 53, 1","author":"Mackie M","year":"1987","unstructured":"Diane\u00a0M Mackie. 1987. Systematic and nonsystematic processing of majority and minority persuasive communications.Journal of Personality and Social Psychology 53, 1 (1987), 41."},{"key":"e_1_3_2_1_47_1","unstructured":"Erwin Marsi and Ferdi\u00a0Van Rooden. 2007. Expressing uncertainty with a talking head in a multimodal question-answering system. https:\/\/api.semanticscholar.org\/CorpusID:2482651"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00494"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594001"},{"key":"e_1_3_2_1_50_1","volume-title":"Pang\u00a0Wei Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi.","author":"Min Sewon","year":"2023","unstructured":"Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen tau Yih, Pang\u00a0Wei Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation. ArXiv abs\/2305.14251 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258841470"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287574"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Mahsan Nourani Samia Kabir Sina Mohseni and Eric\u00a0D. Ragan. 2019. The Effects of Meaningful and Meaningless Explanations on Trust and Perceived System Accuracy in Intelligent Systems. In AAAI Conference on Human Computation & Crowdsourcing. https:\/\/api.semanticscholar.org\/CorpusID:201639081","DOI":"10.1609\/hcomp.v7i1.5284"},{"key":"e_1_3_2_1_53_1","volume-title":"Retrieved","author":"AI.","year":"2022","unstructured":"OpenAI. 2022. Introducing ChatGPT. Retrieved January 17, 2024 from https:\/\/openai.com\/blog\/chatgpt"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502104"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501915"},{"key":"e_1_3_2_1_56_1","unstructured":"Peter\u00a0S. Park Simon Goldstein Aidan O\u2019Gara Michael Chen and Dan Hendrycks. 2023. AI Deception: A Survey of Examples Risks and Potential Solutions. arxiv:cs.CY\/2308.14752"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594043"},{"key":"e_1_3_2_1_59_1","unstructured":"Abhilasha Ravichander Eduard\u00a0H. Hovy Kaheer Suleman Adam Trischler and Jackie Chi\u00a0Kit Cheung. 2020. On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT. In STARSEM. https:\/\/api.semanticscholar.org\/CorpusID:227230677"},{"key":"e_1_3_2_1_60_1","volume-title":"Evaluating Consistency of Question-Answering Models. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:196182403","author":"Ribeiro Marco\u00a0Tulio","year":"2019","unstructured":"Marco\u00a0Tulio Ribeiro, Carlos Guestrin, and Sameer Singh. 2019. Are Red Roses Red? Evaluating Consistency of Question-Answering Models. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:196182403"},{"key":"e_1_3_2_1_61_1","volume-title":"Anchors: High-Precision Model-Agnostic Explanations. In AAAI Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:3366554","author":"Ribeiro Marco\u00a0Tulio","year":"2018","unstructured":"Marco\u00a0Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2018. Anchors: High-Precision Model-Agnostic Explanations. In AAAI Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:3366554"},{"key":"e_1_3_2_1_62_1","volume-title":"International journal of educational technology in higher education 18, 1","author":"Seo Kyoungwon","year":"2021","unstructured":"Kyoungwon Seo, Joice Tang, Ido Roll, Sidney Fels, and Dongwook Yoon. 2021. The impact of artificial intelligence on learner\u2013instructor interaction in online learning. International journal of educational technology in higher education 18, 1 (2021), 1\u201323."},{"key":"e_1_3_2_1_63_1","volume-title":"Comparing Traditional and LLM-based Search for Consumer Choice: A Randomized Experiment. ArXiv abs\/2307.03744","author":"Spatharioti Sofia\u00a0Eleni","year":"2023","unstructured":"Sofia\u00a0Eleni Spatharioti, David\u00a0M. Rothschild, Daniel\u00a0G. Goldstein, and Jake\u00a0M. Hofman. 2023. Comparing Traditional and LLM-based Search for Consumer Choice: A Randomized Experiment. ArXiv abs\/2307.03744 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259375527"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376155"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606756"},{"key":"e_1_3_2_1_66_1","unstructured":"Meiqi Sun Wilson Yan P. Abbeel and Igor Mordatch. 2022. Quantifying Uncertainty in Foundation Models via Ensembles. https:\/\/api.semanticscholar.org\/CorpusID:254183614"},{"key":"e_1_3_2_1_67_1","volume-title":"Med-HALT: Medical Domain Hallucination Test for Large Language Models. In Conference on Computational Natural Language Learning. https:\/\/api.semanticscholar.org\/CorpusID:260316324","author":"Umapathi Logesh\u00a0Kumar","year":"2023","unstructured":"Logesh\u00a0Kumar Umapathi, Ankit Pal, and Malaikannan Sankarasubbu. 2023. Med-HALT: Medical Domain Hallucination Test for Large Language Models. In Conference on Computational Natural Language Learning. https:\/\/api.semanticscholar.org\/CorpusID:260316324"},{"key":"e_1_3_2_1_68_1","volume-title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries. ArXiv abs\/2004.04228","author":"Wang Alex","year":"2020","unstructured":"Alex Wang, Kyunghyun Cho, and Mike Lewis. 2020. Asking and Answering Questions to Evaluate the Factual Consistency of Summaries. ArXiv abs\/2004.04228 (2020). https:\/\/api.semanticscholar.org\/CorpusID:215548661"},{"key":"e_1_3_2_1_69_1","volume-title":"People\u2019s Perceptions Toward Bias and Related Concepts in Large Language Models: A Systematic Review. ArXiv abs\/2309.14504","author":"Wang Lu","year":"2023","unstructured":"Lu Wang, Max Song, Rezvaneh Rezapour, Bum\u00a0Chul Kwon, and Jina Huh-Yoo. 2023. People\u2019s Perceptions Toward Bias and Related Concepts in Large Language Models: A Systematic Review. ArXiv abs\/2309.14504 (2023). https:\/\/api.semanticscholar.org\/CorpusID:262825989"},{"key":"e_1_3_2_1_70_1","volume-title":"Ed\u00a0Huai hsin Chi, and Denny Zhou","author":"Wang Xuezhi","year":"2022","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed\u00a0Huai hsin Chi, and Denny Zhou. 2022. Self-Consistency Improves Chain of Thought Reasoning in Language Models. ArXiv abs\/2203.11171 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247595263"},{"key":"e_1_3_2_1_71_1","volume-title":"IUI Workshops. https:\/\/api.semanticscholar.org\/CorpusID:255825625","author":"Weisz D.","year":"2023","unstructured":"Justin\u00a0D. Weisz, Michael\u00a0J. Muller, Jessica He, and Stephanie Houde. 2023. Toward General Design Principles for Generative AI Applications 130-144. In IUI Workshops. https:\/\/api.semanticscholar.org\/CorpusID:255825625"},{"key":"e_1_3_2_1_72_1","first-page":"2245","article-title":"Artificial intelligence, artificial teachers and the fate of learners in the 21st century education sector: Implications for theory and practice","volume":"119","author":"Ayodele\u00a0Power Wogu Ikedinachi","year":"2018","unstructured":"Ikedinachi Ayodele\u00a0Power Wogu, Sanjay Misra, Esther\u00a0Fadeke Olu-Owolabi, Patrick\u00a0A Assibong, Oluwakemei\u00a0D Udoh, SO Ogiri, and R Damasevicius. 2018. Artificial intelligence, artificial teachers and the fate of learners in the 21st century education sector: Implications for theory and practice. International Journal of Pure and Applied Mathematics 119, 16 (2018), 2245\u20132259.","journal-title":"International Journal of Pure and Applied Mathematics"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300509"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517791"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372852"},{"key":"e_1_3_2_1_76_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:cs.CL\/2303.18223"},{"key":"e_1_3_2_1_77_1","volume-title":"Navigating the Grey Area: Expressions of Overconfidence and Uncertainty in Language Models. ArXiv abs\/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 abs\/2302.13439 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257220189"}],"event":{"name":"FAccT '24: The 2024 ACM Conference on Fairness, Accountability, and Transparency","location":"Rio de Janeiro Brazil","acronym":"FAccT '24"},"container-title":["The 2024 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630106.3662681","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3630106.3662681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:57:08Z","timestamp":1750291028000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630106.3662681"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,3]]},"references-count":77,"alternative-id":["10.1145\/3630106.3662681","10.1145\/3630106"],"URL":"https:\/\/doi.org\/10.1145\/3630106.3662681","relation":{},"subject":[],"published":{"date-parts":[[2024,6,3]]},"assertion":[{"value":"2024-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}