{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T21:55:13Z","timestamp":1783547713499,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,26]]},"DOI":"10.1145\/3624918.3625329","type":"proceedings-article","created":{"date-parts":[[2023,11,23]],"date-time":"2023-11-23T08:49:17Z","timestamp":1700729357000},"page":"46-51","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":48,"title":["ChatGPT Hallucinates when Attributing Answers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0271-5563","authenticated-orcid":false,"given":"Guido","family":"Zuccon","sequence":"first","affiliation":[{"name":"ITEE, The University of Queensland, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5577-3391","authenticated-orcid":false,"given":"Bevan","family":"Koopman","sequence":"additional","affiliation":[{"name":"e-Health, CSIRO, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5005-6091","authenticated-orcid":false,"given":"Razia","family":"Shaik","sequence":"additional","affiliation":[{"name":"The University of Queensland, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,11,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models. arXiv preprint arXiv:2212.08037","author":"Bohnet Bernd","year":"2022","unstructured":"Bernd Bohnet, Vinh\u00a0Q Tran, Pat Verga, Roee Aharoni, Daniel Andor, Livio\u00a0Baldini Soares, Jacob Eisenstein, Kuzman Ganchev, Jonathan Herzig, Kai Hui, 2022. Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models. arXiv preprint arXiv:2212.08037 (2022)."},{"key":"e_1_3_2_1_2_1","volume-title":"RARR: Researching and Revising What Language Models Say, Using Language Models. arXiv preprint arXiv:2210.08726v2","author":"Gao Luyu","year":"2022","unstructured":"Luyu Gao, Zhuyun Dai, Panupong Pasupat, Anthony Chen, Arun\u00a0Tejasvi Chaganty, Yicheng Fan, Vincent\u00a0Y Zhao, Ni Lao, Hongrae Lee, Da-Cheng Juan, 2022. RARR: Researching and Revising What Language Models Say, Using Language Models. arXiv preprint arXiv:2210.08726v2 (2022)."},{"key":"e_1_3_2_1_3_1","volume-title":"Enabling Large Language Models to Generate Text with Citations. arXiv preprint arXiv:2305.14627","author":"Gao Tianyu","year":"2023","unstructured":"Tianyu Gao, Howard Yen, Jiatong Yu, and Danqi Chen. 2023. Enabling Large Language Models to Generate Text with Citations. arXiv preprint arXiv:2305.14627 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"ChatGPT is not all you need. A State of the Art Review of large Generative AI models. arXiv preprint arXiv:2301.04655","author":"Gozalo-Brizuela Roberto","year":"2023","unstructured":"Roberto Gozalo-Brizuela and Eduardo\u00a0C Garrido-Merchan. 2023. ChatGPT is not all you need. A State of the Art Review of large Generative AI models. arXiv preprint arXiv:2301.04655 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mcpdig.2023.05.004"},{"key":"e_1_3_2_1_6_1","volume-title":"How close is chatgpt to human experts? comparison corpus, evaluation, and detection. arXiv preprint arXiv:2301.07597","author":"Guo Biyang","year":"2023","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 preprint arXiv:2301.07597 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Quality of citation data using the natural language processing tool ChatGPT in rheumatology: creation of false references. RMD open 9, 2","author":"Hueber J","year":"2023","unstructured":"Axel\u00a0J Hueber and Arnd Kleyer. 2023. Quality of citation data using the natural language processing tool ChatGPT in rheumatology: creation of false references. RMD open 9, 2 (2023), e003248."},{"key":"e_1_3_2_1_8_1","volume-title":"Exploring ChatGPT\u2019s Ability to Rank Content: A Preliminary Study on Consistency with Human Preferences. arXiv preprint arXiv:2303.07610","author":"Ji Yunjie","year":"2023","unstructured":"Yunjie Ji, Yan Gong, Yiping Peng, Chao Ni, Peiyan Sun, Dongyu Pan, Baochang Ma, and Xiangang Li. 2023. Exploring ChatGPT\u2019s Ability to Rank Content: A Preliminary Study on Consistency with Human Preferences. arXiv preprint arXiv:2303.07610 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_1_10_1","volume-title":"Shengyao Zhuang, Simon Gibson, Yash Dang, David Lawrence, and Guido Zuccon.","author":"Koopman Bevan","year":"2023","unstructured":"Bevan Koopman, Ahmed Mourad, Hang Li, Anton van\u00a0der Vegt, Shengyao Zhuang, Simon Gibson, Yash Dang, David Lawrence, and Guido Zuccon. 2023. AgAsk: an agent to help answer farmer\u2019s questions from scientific documents. International Journal on Digital Libraries (2023), 1\u201316."},{"key":"e_1_3_2_1_11_1","volume-title":"Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958","author":"Lin Stephanie","year":"2021","unstructured":"Stephanie Lin, Jacob Hilton, and Owain Evans. 2021. Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958 (2021)."},{"key":"e_1_3_2_1_12_1","volume-title":"Teaching language models to support answers with verified quotes. arXiv preprint arXiv:2203.11147","author":"Menick Jacob","year":"2022","unstructured":"Jacob Menick, Maja Trebacz, Vladimir Mikulik, John Aslanides, Francis Song, Martin Chadwick, Mia Glaese, Susannah Young, Lucy Campbell-Gillingham, Geoffrey Irving, 2022. Teaching language models to support answers with verified quotes. arXiv preprint arXiv:2203.11147 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3476415.3476428"},{"key":"e_1_3_2_1_14_1","volume-title":"Chatgpt versus traditional question answering for knowledge graphs: Current status and future directions towards knowledge graph chatbots. arXiv preprint arXiv:2302.06466","author":"Omar Reham","year":"2023","unstructured":"Reham Omar, Omij Mangukiya, Panos Kalnis, and Essam Mansour. 2023. Chatgpt versus traditional question answering for knowledge graphs: Current status and future directions towards knowledge graph chatbots. arXiv preprint arXiv:2302.06466 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"Scaling language models: Methods, analysis & insights from training gopher. arXiv preprint arXiv:2112.11446","author":"Rae W","year":"2021","unstructured":"Jack\u00a0W Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican, Jordan Hoffmann, Francis Song, John Aslanides, Sarah Henderson, Roman Ring, Susannah Young, 2021. Scaling language models: Methods, analysis & insights from training gopher. arXiv preprint arXiv:2112.11446 (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Hannah Rashkin Vitaly Nikolaev Matthew Lamm Lora Aroyo Michael Collins Dipanjan Das Slav Petrov Gaurav Singh\u00a0Tomar Iulia Turc and David Reitter. [n.d.]. Measuring attribution in natural language generation models. Computational Linguistics ([n. d.]) 1\u201366.","DOI":"10.1162\/coli_a_00490"},{"key":"e_1_3_2_1_17_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_18_1","volume-title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent. arXiv preprint arXiv:2304.09542","author":"Sun Weiwei","year":"2023","unstructured":"Weiwei Sun, Lingyong Yan, Xinyu Ma, Pengjie Ren, Dawei Yin, and Zhaochun Ren. 2023. Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent. arXiv preprint arXiv:2304.09542 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Evaluation of ChatGPT as a question answering system for answering complex questions. arXiv preprint arXiv:2303.07992","author":"Tan Yiming","year":"2023","unstructured":"Yiming Tan, Dehai Min, Yu Li, Wenbo Li, Nan Hu, Yongrui Chen, and Guilin Qi. 2023. Evaluation of ChatGPT as a question answering system for answering complex questions. arXiv preprint arXiv:2303.07992 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Lamda: Language models for dialog applications. arXiv preprint arXiv:2201.08239","author":"Thoppilan Romal","year":"2022","unstructured":"Romal Thoppilan, Daniel De\u00a0Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, 2022. Lamda: Language models for dialog applications. arXiv preprint arXiv:2201.08239 (2022)."},{"key":"e_1_3_2_1_21_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_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533088"},{"key":"e_1_3_2_1_23_1","volume-title":"tell me what I want to hear: How prompt knowledge impacts health answer correctness. arXiv preprint arXiv:2302.13793","author":"Zuccon Guido","year":"2023","unstructured":"Guido Zuccon and Bevan Koopman. 2023. Dr ChatGPT, tell me what I want to hear: How prompt knowledge impacts health answer correctness. arXiv preprint arXiv:2302.13793 (2023)."}],"event":{"name":"SIGIR-AP '23: Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","location":"Beijing China","acronym":"SIGIR-AP '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624918.3625329","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624918.3625329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T21:32:29Z","timestamp":1755898349000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624918.3625329"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,26]]},"references-count":23,"alternative-id":["10.1145\/3624918.3625329","10.1145\/3624918"],"URL":"https:\/\/doi.org\/10.1145\/3624918.3625329","relation":{},"subject":[],"published":{"date-parts":[[2023,11,26]]},"assertion":[{"value":"2023-11-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}