{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T14:57:39Z","timestamp":1776092259098,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T00:00:00Z","timestamp":1709510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,4]]},"DOI":"10.1145\/3616855.3635856","type":"proceedings-article","created":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T18:18:12Z","timestamp":1709576292000},"page":"8-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":58,"title":["Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4046-3419","authenticated-orcid":false,"given":"Zahra","family":"Abbasiantaeb","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7275-5398","authenticated-orcid":false,"given":"Yifei","family":"Yuan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8312-0694","authenticated-orcid":false,"given":"Evangelos","family":"Kanoulas","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9447-4172","authenticated-orcid":false,"given":"Mohammad","family":"Aliannejadi","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2024,3,4]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Herv\u00e9 Abdi. 2007. The Kendall Rank Correlation Coefficient. arXiv abs\/1507.01427."},{"key":"e_1_3_2_1_2_1","volume-title":"Krisztian Balog, and Shuo Zhang.","author":"Afzali Jafar","year":"2023","unstructured":"Jafar Afzali, Aleksander Mark Drzewiecki, Krisztian Balog, and Shuo Zhang. 2023. UserSimCRS: A User Simulation Toolkit for Evaluating Conversational Recommender Systems. arXiv abs\/2301.05544 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Can we trust the evaluation on ChatGPT? arXiv abs\/2303.12767","author":"Aiyappa Rachith","year":"2023","unstructured":"Rachith Aiyappa, Jisun An, Haewoon Kwak, and Yong-Yeol Ahn. 2023. Can we trust the evaluation on ChatGPT? arXiv abs\/2303.12767 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.","author":"Aliannejadi Mohammad","unstructured":"Mohammad Aliannejadi, Hamed Zamani, Fabio Crestani, and W. Bruce Croft. 2019. Asking Clarifying Questions in Open-Domain Information-Seeking Conversations. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval."},{"key":"e_1_3_2_1_5_1","volume-title":"Generating Synthetic Documents for Cross-Encoder Re-Rankers: A Comparative Study of ChatGPT and Human Experts. arXiv abs\/2305.02320","author":"Askari Arian","year":"2023","unstructured":"Arian Askari, Mohammad Aliannejadi, E. Kanoulas, and Suzan Verberne. 2023. Generating Synthetic Documents for Cross-Encoder Re-Rankers: A Comparative Study of ChatGPT and Human Experts. arXiv abs\/2305.02320 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615111"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Second International Conference on Design of Experimental Search & Information REtrieval Systems","volume":"2950","author":"Balog Krisztian","year":"2021","unstructured":"Krisztian Balog. 2021. Conversational AI from an Information Retrieval Perspective: Remaining Challenges and a Case for User Simulation. In Proceedings of the Second International Conference on Design of Experimental Search & Information REtrieval Systems, Vol. 2950."},{"key":"e_1_3_2_1_8_1","volume-title":"User Simulation for Evaluating Information Access Systems. arXiv abs\/2306.08550","author":"Balog Krisztian","year":"2023","unstructured":"Krisztian Balog and ChengXiang Zhai. 2023. User Simulation for Evaluating Information Access Systems. arXiv abs\/2306.08550 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"scripts, and information-seeking strategies: On the design of interactive information retrieval systems. Expert Systems With Applications 9","author":"Belkin Nicholas J.","year":"1995","unstructured":"Nicholas J. Belkin, Colleen Cool, Adelheit Stein, and Ulrich Thiel. 1995. Cases, scripts, and information-seeking strategies: On the design of interactive information retrieval systems. Expert Systems With Applications 9 (1995)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063576.2063668"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1241"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358016"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"W. Bruce Croft and R. H. Thompson. 1987. I3R: A new approach to the design of document retrieval systems. J. Am. Soc. Inf. Sci. 38 (1987).","DOI":"10.1002\/(SICI)1097-4571(198711)38:6<389::AID-ASI1>3.0.CO;2-4"},{"key":"e_1_3_2_1_14_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv abs\/1810.04805","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv abs\/1810.04805 (2019)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578337.3605136"},{"key":"e_1_3_2_1_16_1","volume-title":"How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection. arXiv abs\/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 abs\/2301.07597 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Bryan Hooi, and Aldo Lipani.","author":"Hu Zhiyuan","year":"2023","unstructured":"Zhiyuan Hu, Yue Feng, Anh Tuan Luu, Bryan Hooi, and Aldo Lipani. 2023. Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System. arXiv abs\/2306.09821 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3587368"},{"key":"e_1_3_2_1_19_1","volume-title":"FlowQA: Grasping Flow in History for Conversational Machine Comprehension. arXiv abs\/1810.06683","author":"Huang Hsin-Yuan","year":"2018","unstructured":"Hsin-Yuan Huang, Eunsol Choi, and Wen tau Yih. 2018. FlowQA: Grasping Flow in History for Conversational Machine Comprehension. arXiv abs\/1810.06683 (2018)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1167"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772746"},{"key":"e_1_3_2_1_22_1","volume-title":"Lan","author":"Kumar Nischal Ashok","year":"2023","unstructured":"Nischal Ashok Kumar, Nigel Fernandez, Zichao Wang, and Andrew S. Lan. 2023. Improving Reading Comprehension Question Generation with Data Augmentation and Overgenerate-and-rank. arXiv abs\/2306.08847 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"ChatGPT: Beginning of an End of Manual Linguistic Data Annotation? Use Case of Automatic Genre Identification. arXiv abs\/2303.03953","author":"Kuzman Taja","year":"2023","unstructured":"Taja Kuzman, Igor Mozeti, and Nikola Ljubesic. 2023. ChatGPT: Beginning of an End of Manual Linguistic Data Annotation? Use Case of Automatic Genre Identification. arXiv abs\/2303.03953 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 4th International Conference on Learning Representations.","author":"Li Jiwei","year":"2016","unstructured":"Jiwei Li, Alexander H. Miller, Sumit Chopra, Marc'Aurelio Ranzato, and Jason Weston. 2016. Learning through Dialogue Interactions by Asking Questions. In Proceedings of the 4th International Conference on Learning Representations."},{"key":"e_1_3_2_1_25_1","volume-title":"A Unified MRC Framework for Named Entity Recognition. arXiv abs\/1910.11476","author":"Li Xiaoya","year":"2019","unstructured":"Xiaoya Li, Jingrong Feng, Yuxian Meng, Qinghong Han, FeiWu, and Jiwei Li. 2019. A Unified MRC Framework for Named Entity Recognition. arXiv abs\/1910.11476 (2019)."},{"key":"e_1_3_2_1_26_1","volume-title":"Simulation studies of different dimensions of users' interests and their impact on user modeling and information filtering. Information Retrieval 6","author":"Mostafa Javed","year":"2003","unstructured":"Javed Mostafa, Snehasis Mukhopadhyay, and Mathew Palakal. 2003. Simulation studies of different dimensions of users' interests and their impact on user modeling and information filtering. Information Retrieval 6 (2003)."},{"key":"e_1_3_2_1_27_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv abs\/2303.08774 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591683"},{"key":"e_1_3_2_1_29_1","volume-title":"Percy Liang, and Michael S.","author":"Park Joon Sung","year":"2023","unstructured":"Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein. 2023. Generative Agents: Interactive Simulacra of Human Behavior. arXiv abs\/2304.03442 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545616"},{"key":"e_1_3_2_1_31_1","volume-title":"or not to ChatGPT: That is the question! arXiv abs\/2304.01487","author":"Pegoraro Alessandro","year":"2023","unstructured":"Alessandro Pegoraro, Kavita Kumari, Hossein Fereidooni, and Ahmad-Reza Sadeghi. 2023. To ChatGPT, or not to ChatGPT: That is the question! arXiv abs\/2304.01487 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.159"},{"key":"e_1_3_2_1_33_1","volume-title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver? arXiv abs\/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 abs\/2302.06476 (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401110"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331341"},{"key":"e_1_3_2_1_36_1","volume":"201","author":"Raffel Colin","unstructured":"Colin Raffel, Noam M. Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou,Wei Li, and Peter J. Liu. 2019. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. arXiv abs\/1910.10683(2019).","journal-title":"Peter J. Liu."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_1_38_1","volume-title":"Manning","author":"Reddy Siva","year":"2018","unstructured":"Siva Reddy, Danqi Chen, and Christopher D. Manning. 2018. CoQA: A Conversational Question Answering Challenge. Transactions of the Association for Computational Linguistics 7 (2018)."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence.","author":"Saha Amrita","unstructured":"Amrita Saha, Vardaan Pahuja, Mitesh M. Khapra, Karthik Sankaranarayanan, and A. P. Sarath Chandar. 2018. Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph. In Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_40_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv abs\/1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv abs\/1910.01108 (2019)."},{"key":"e_1_3_2_1_41_1","volume-title":"Toolformer: Language Models Can Teach Themselves to Use Tools. arXiv abs\/2302.04761","author":"Schick Timo","year":"2023","unstructured":"Timo Schick, Jane Dwivedi-Yu, Roberto Dess\u00ec, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language Models Can Teach Themselves to Use Tools. arXiv abs\/2302.04761 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498440"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531798"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463241"},{"key":"e_1_3_2_1_45_1","volume-title":"Evaluation of ChatGPT as a Question Answering System for Answering Complex Questions. arXiv abs\/2303.07992","author":"Tan Yiming","year":"2023","unstructured":"Yiming Tan, Dehai Min, Y. Li, Wenbo Li, Na Hu, Yongrui Chen, and Guilin Qi. 2023. Evaluation of ChatGPT as a Question Answering System for Answering Complex Questions. arXiv abs\/2303.07992 (2023)."},{"key":"e_1_3_2_1_46_1","volume-title":"Does Synthetic Data Generation of LLMs Help Clinical Text Mining? arXiv abs\/2303.04360","author":"Tang Ruixiang","year":"2023","unstructured":"Ruixiang Tang, Xiaotian Han, Xiaoqian Jiang, and Xia Hu. 2023. Does Synthetic Data Generation of LLMs Help Clinical Text Mining? arXiv abs\/2303.04360 (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"In-Context Learning User Simulators for Task-Oriented Dialog Systems. arXiv abs\/2306.00774","author":"Terragni Silvia","year":"2023","unstructured":"Silvia Terragni, Modestas Filipavicius, Nghia Khau, Bruna Guedes, Andr\u00e9 Manso, and Roland Mathis. 2023. In-Context Learning User Simulators for Task-Oriented Dialog Systems. arXiv abs\/2306.00774 (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"LLaMA: Open and Efficient Foundation Language Models. arXiv abs\/2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv abs\/2302.13971 (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the 1st Workshop on Representation Learning for NLP.","author":"Trischler Adam","year":"2016","unstructured":"Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, and Kaheer Suleman. 2016. NewsQA: A Machine Comprehension Dataset. In Proceedings of the 1st Workshop on Representation Learning for NLP."},{"key":"e_1_3_2_1_50_1","volume-title":"LLM-powered Data Augmentation for Enhanced Crosslingual Performance. arXiv abs\/2305.14288","author":"Whitehouse Chenxi","year":"2023","unstructured":"Chenxi Whitehouse, Monojit Choudhury, and Alham Fikri Aji. 2023. LLM-powered Data Augmentation for Enhanced Crosslingual Performance. arXiv abs\/2305.14288 (2023)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.34"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5812"},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of Knowledge and Information Systems 64","author":"Zaib Munazza","year":"2021","unstructured":"Munazza Zaib, Wei Emma Zhang, Quan Z. Sheng, Adnan Mahmood, and Yang Zhang. 2021. Conversational question answering: a survey. Proceedings of Knowledge and Information Systems 64 (2021)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403202"},{"key":"e_1_3_2_1_55_1","volume-title":"RoR: Read-over-Read for Long Document Machine Reading Comprehension. arXiv abs\/2109.04780","author":"Zhao Jing","year":"2021","unstructured":"Jing Zhao, Junwei Bao, Yifan Wang, Yongwei Zhou, Youzheng Wu, Xiaodong He, and Bowen Zhou. 2021. RoR: Read-over-Read for Long Document Machine Reading Comprehension. arXiv abs\/2109.04780 (2021)."},{"key":"e_1_3_2_1_56_1","volume-title":"A Survey of Large Language Models. arXiv abs\/2303.18223","author":"Zhao Wayne Xin","year":"2023","unstructured":"Wayne Xin 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, Z. Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jianyun Nie, and Ji rong Wen. 2023. A Survey of Large Language Models. arXiv abs\/2303.18223 (2023)."},{"key":"e_1_3_2_1_57_1","volume-title":"Pan Hui, and Gareth Tyson.","author":"Zhu Yiming","year":"2023","unstructured":"Yiming Zhu, Peixian Zhang, Ehsan ul Haq, Pan Hui, and Gareth Tyson. 2023. Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks. arXiv abs\/2304.10145 (2023)."}],"event":{"name":"WSDM '24: The 17th ACM International Conference on Web Search and Data Mining","location":"Merida Mexico","acronym":"WSDM '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 17th ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635856","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3616855.3635856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:51:10Z","timestamp":1755823870000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635856"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,4]]},"references-count":57,"alternative-id":["10.1145\/3616855.3635856","10.1145\/3616855"],"URL":"https:\/\/doi.org\/10.1145\/3616855.3635856","relation":{},"subject":[],"published":{"date-parts":[[2024,3,4]]},"assertion":[{"value":"2024-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}