{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:50:11Z","timestamp":1776117011393,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-sa\/4.0\/"}],"funder":[{"name":"HIDSS4Health?Helmholtz Information and Data Science School for Health"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613904.3642428","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:39:12Z","timestamp":1715416752000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":55,"title":["HILL: A Hallucination Identifier for Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5347-0493","authenticated-orcid":false,"given":"Florian","family":"Leiser","sequence":"first","affiliation":[{"name":"Insitute of Applied Informatics and Formal Description Methods, Department of Economics and Management, Karlsruhe Institute of Technology (KIT), Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4713-8408","authenticated-orcid":false,"given":"Sven","family":"Eckhardt","sequence":"additional","affiliation":[{"name":"Department of Informatics, University of Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8938-302X","authenticated-orcid":false,"given":"Valentin","family":"Leuthe","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5108-4609","authenticated-orcid":false,"given":"Merlin","family":"Knaeble","sequence":"additional","affiliation":[{"name":"Human-Centered Systems Lab, Karlsruhe Institute of Technology (KIT), Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6546-4816","authenticated-orcid":false,"given":"Alexander","family":"M\u00e4dche","sequence":"additional","affiliation":[{"name":"Human-Centered Systems Lab, Karlsruhe Institute of Technology (KIT), Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0453-9762","authenticated-orcid":false,"given":"Gerhard","family":"Schwabe","sequence":"additional","affiliation":[{"name":"Department of Informatics, University of Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4353-8519","authenticated-orcid":false,"given":"Ali","family":"Sunyaev","sequence":"additional","affiliation":[{"name":"Insitute of Applied Informatics and Formal Description Methods, Department of Economics and Management, Karlsruhe Institute of Technology (KIT), Germany"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_1_1","doi-asserted-by":"publisher","DOI":"10.1080\/10447310802205776"},{"key":"e_1_3_3_3_2_1","unstructured":"Emily Bell. 2023. A fake news frenzy: why ChatGPT could be disastrous for truth in journalism. https:\/\/www.theguardian.com\/commentisfree\/2023\/mar\/03\/fake-news-chatgpt-truth-journalism-disinformation"},{"key":"e_1_3_3_3_3_1","doi-asserted-by":"crossref","unstructured":"Ali Borji. 2023. A Categorical Archive of ChatGPT Failures.","DOI":"10.21203\/rs.3.rs-2895792\/v1"},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1939.tb02219.x"},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_3_3_6_1","unstructured":"Dmitri Brereton. 2023. Bing AI Can\u2019t Be Trusted. https:\/\/dkb.blog\/p\/bing-ai-cant-be-trusted"},{"key":"e_1_3_3_3_7_1","unstructured":"Greg Brockman Mira Murati Peter Welinder and OpenAI. 2020. OpenAI API \u2014 openai.com. https:\/\/openai.com\/blog\/openai-api. [Accessed 25-08-2023]."},{"key":"e_1_3_3_3_8_1","volume-title":"\u201cquick and dirty\u2019usability. Usability evaluation in industry 189, 3","author":"Brooke John","year":"1996","unstructured":"John Brooke. 1996. Sus: a \u201cquick and dirty\u2019usability. Usability evaluation in industry 189, 3 (1996), 189\u2013194."},{"key":"e_1_3_3_3_9_1","volume-title":"Proceedings of the 30th USENIX Security Symposium, Vol.\u00a06. The USENIX Association, 2633\u20132650","author":"Carlini Nicholas","year":"2021","unstructured":"Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom\u00a0B Brown, Dawn Song, Ulfar Erlingsson, 2021. Extracting Training Data from Large Language Models.. In Proceedings of the 30th USENIX Security Symposium, Vol.\u00a06. The USENIX Association, 2633\u20132650."},{"key":"e_1_3_3_3_10_1","volume-title":"Sawtooth Software Conference Proceedings, Vol.\u00a0530","author":"Cohen Steve","year":"2003","unstructured":"Steve Cohen 2003. Maximum difference scaling: improved measures of importance and preference for segmentation. In Sawtooth Software Conference Proceedings, Vol.\u00a0530. Sawtooth Software, Inc. Fir St., Sequim, WA, 61\u201374."},{"key":"e_1_3_3_3_11_1","volume-title":"Alphabet shares dive after Google AI chatbot Bard flubs answer in ad","author":"Coulter Martin","year":"2023","unstructured":"Martin Coulter and Greg Bensinger. 2023. Alphabet shares dive after Google AI chatbot Bard flubs answer in ad. Reuters (Feb. 2023). https:\/\/www.reuters.com\/technology\/google-ai-chatbot-bard-offers-inaccurate-information-company-ad-2023-02-08\/"},{"key":"e_1_3_3_3_12_1","unstructured":"Vue.js developers. 2014. Vue.js - The Progressive JavaScript Framework v3.0. https:\/\/vuejs.org\/guide\/introduction.html Accessed: 2023-08-25."},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2005.93"},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-42286-7_2"},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1177\/074391569201100202"},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2308(91)90019-M"},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"crossref","unstructured":"Boris\u00a0A Galitsky. 2023. Truth-O-Meter: Collaborating with LLM in Fighting its Hallucinations.","DOI":"10.20944\/preprints202307.1723.v1"},{"key":"e_1_3_3_3_18_1","volume-title":"RARR: Researching and Revising What Language Models Say, Using Language Models.","author":"Gao Luyu","year":"2023","unstructured":"Luyu Gao, Zhuyun Dai, Panupong Pasupat, Anthony Chen, Arun\u00a0Tejasvi Chaganty, Yicheng Fan, Vincent\u00a0Y. Zhao, Ni Lao, Hongrae Lee, Da-Cheng Juan, and Kelvin Guu. 2023. RARR: Researching and Revising What Language Models Say, Using Language Models."},{"key":"e_1_3_3_3_19_1","unstructured":"Google. 2021. LaMDA: our breakthrough conversation technology. https:\/\/blog.google\/technology\/ai\/lamda\/"},{"key":"e_1_3_3_3_20_1","volume-title":"\u00a0T. Martins","author":"Guerreiro M.","year":"2023","unstructured":"Nuno\u00a0M. Guerreiro, Duarte Alves, Jonas Waldendorf, Barry Haddow, Alexandra Birch, Pierre Colombo, and Andr\u00e9 F.\u00a0T. Martins. 2023. Hallucinations in Large Multilingual Translation Models. arxiv:2303.16104\u00a0[cs.CL]"},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/DISA.2018.8490530"},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1080\/10584609.2018.1426662"},{"key":"e_1_3_3_3_24_1","unstructured":"Vivian Lai Chacha Chen Q\u00a0Vera Liao Alison Smith-Renner and Chenhao Tan. 2021. Towards a science of human-ai decision making: a survey of empirical studies."},{"key":"e_1_3_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1518\/hfes.46.1.50.30392"},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603555.3603565"},{"key":"e_1_3_3_3_27_1","volume-title":"Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models. arXiv preprint arXiv:2303.08896","author":"Manakul Potsawee","year":"2023","unstructured":"Potsawee Manakul, Adian Liusie, and Mark\u00a0JF Gales. 2023. Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models. arXiv preprint arXiv:2303.08896 (2023)."},{"key":"e_1_3_3_3_28_1","volume-title":"On faithfulness and factuality in abstractive summarization. arXiv preprint arXiv:2005.00661","author":"Maynez Joshua","year":"2020","unstructured":"Joshua Maynez, Shashi Narayan, Bernd Bohnet, and Ryan McDonald. 2020. On faithfulness and factuality in abstractive summarization. arXiv preprint arXiv:2005.00661 (2020)."},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infoandorg.2006.11.001"},{"key":"e_1_3_3_3_30_1","unstructured":"Jyoti Narayan Krystal Hu Martin Coulter and Supantha Mukherjee. 2023. Elon Musk and others urge ai pause citing \u2019risks to society\u2019. https:\/\/www.reuters.com\/technology\/musk-experts-urge-pause-training-ai-systems-that-can-outperform-gpt-4-2023-03-29\/ Publication Title: Reuters."},{"key":"e_1_3_3_3_32_1","unstructured":"OpenAI. 2023. Introducing ChatGPT. https:\/\/openai.com\/blog\/chatgpt"},{"key":"e_1_3_3_3_33_1","volume-title":"Advances in Neural Information Processing Systems, S.\u00a0Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, D.\u00a0Belgrave, K.\u00a0Cho, and A.\u00a0Oh (Eds.). Vol.\u00a035. Curran Associates","author":"Ouyang Long","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul\u00a0F Christiano, Jan Leike, and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems, S.\u00a0Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, D.\u00a0Belgrave, K.\u00a0Cho, and A.\u00a0Oh (Eds.). Vol.\u00a035. Curran Associates, Inc., 27730\u201327744."},{"key":"e_1_3_3_3_34_1","volume-title":"Humans and automation: Use, misuse, disuse, abuse. Human factors 39, 2","author":"Parasuraman Raja","year":"1997","unstructured":"Raja Parasuraman and Victor Riley. 1997. Humans and automation: Use, misuse, disuse, abuse. Human factors 39, 2 (1997), 230\u2013253."},{"key":"e_1_3_3_3_35_1","volume-title":"Overreliance on AI Literature Review. Microsoft Research","author":"Passi Samir","year":"2022","unstructured":"Samir Passi and Mihaela Vorvoreanu. 2022. Overreliance on AI Literature Review. Microsoft Research (2022)."},{"key":"e_1_3_3_3_36_1","volume-title":"Check your facts and try again: Improving large language models with external knowledge and automated feedback. arXiv preprint arXiv:2302.12813","author":"Peng Baolin","year":"2023","unstructured":"Baolin Peng, Michel Galley, Pengcheng He, Hao Cheng, Yujia Xie, Yu Hu, Qiuyuan Huang, Lars Liden, Zhou Yu, Weizhu Chen, 2023. Check your facts and try again: Improving large language models with external knowledge and automated feedback. arXiv preprint arXiv:2302.12813 (2023)."},{"key":"e_1_3_3_3_37_1","volume-title":"Know What You Don\u2019t Know: Unanswerable Questions for SQuAD. CoRR abs\/1806.03822","author":"Rajpurkar Pranav","year":"2018","unstructured":"Pranav Rajpurkar, Robin Jia, and Percy Liang. 2018. Know What You Don\u2019t Know: Unanswerable Questions for SQuAD. CoRR abs\/1806.03822 (2018). arXiv:1806.03822http:\/\/arxiv.org\/abs\/1806.03822"},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"crossref","unstructured":"Vikas Raunak Arul Menezes and Marcin Junczys-Dowmunt. 2021. The Curious Case of Hallucinations in Neural Machine Translation. arxiv:2104.06683\u00a0[cs.CL]","DOI":"10.18653\/v1\/2021.naacl-main.92"},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.5898\/JHRI.1.1.Riek"},{"key":"e_1_3_3_3_40_1","unstructured":"Michael Schade. 2021. What Does the Official ChatGPT iOS App Icon Look Like? | OpenAI Help Center \u2014 help.openai.com. https:\/\/help.openai.com\/en\/articles\/7905742-what-does-the-official-chatgpt-ios-app-icon-look-like. [Accessed 25-08-2023]."},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584066"},{"key":"e_1_3_3_3_42_1","unstructured":"Jessica Shieh. 2023. Best practices for prompt engineering with OpenAI API | OpenAI Help Center \u2014 help.openai.com. https:\/\/help.openai.com\/en\/articles\/6654000-best-practices-for-prompt-engineering-with-openai-api. [Accessed 29-08-2023]."},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2020.1741118"},{"key":"e_1_3_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12525-020-00441-4"},{"key":"e_1_3_3_3_45_1","volume-title":"Internationale Tagung Wirtschaftsinformatik","author":"Tomitza Christoph","year":"2023","unstructured":"Christoph Tomitza, Myriam Schaschek, Lisa Straub, and Axel Winkelmann. forthcoming. What is the Minimum to Trust AI?\u2014A Requirement Analysis for (Generative) AI-based Texts. In Internationale Tagung Wirtschaftsinformatik 2023."},{"key":"e_1_3_3_3_46_1","unstructured":"James Vincent. 2023. Google and Microsoft\u2019s chatbots are already citing one another in a misinformation shitshow. https:\/\/www.theverge.com\/2023\/3\/22\/23651564\/google-microsoft-bard-bing-chatbots-misinformation"},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3079836"},{"key":"e_1_3_3_3_48_1","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:2302.11382\u00a0[cs.SE]"},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"publisher","unstructured":"Jingfeng Yang Hongye Jin Ruixiang Tang Xiaotian Han Qizhang Feng Haoming Jiang Bing Yin and Xia Hu. 2023. Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond. https:\/\/doi.org\/10.48550\/ARXIV.2304.13712","DOI":"10.48550\/ARXIV.2304.13712"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"key":"e_1_3_3_3_51_1","volume-title":"Siren\u2019s Song in the AI Ocean: A Survey on Hallucination in Large Language Models. arXiv preprint arXiv:2309.01219","author":"Zhang Yue","year":"2023","unstructured":"Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, 2023. Siren\u2019s Song in the AI Ocean: A Survey on Hallucination in Large Language Models. arXiv preprint arXiv:2309.01219 (2023)."},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"crossref","unstructured":"Zheng Zhao Shay\u00a0B. Cohen and Bonnie Webber. 2020. Reducing Quantity Hallucinations in Abstractive Summarization. arxiv:2009.13312\u00a0[cs.CL]","DOI":"10.18653\/v1\/2020.findings-emnlp.203"},{"key":"e_1_3_3_3_53_1","unstructured":"Yiyang Zhou Chenhang Cui Jaehong Yoon Linjun Zhang Zhun Deng Chelsea Finn Mohit Bansal and Huaxiu Yao. 2023. Analyzing and Mitigating Object Hallucination in Large Vision-Language Models. arxiv:2310.00754\u00a0[cs.LG]"}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Proceedings of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642428","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613904.3642428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:56:47Z","timestamp":1750291007000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642428"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":52,"alternative-id":["10.1145\/3613904.3642428","10.1145\/3613904"],"URL":"https:\/\/doi.org\/10.1145\/3613904.3642428","relation":{},"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}