{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T01:01:27Z","timestamp":1790989287953,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T00:00:00Z","timestamp":1726444800000},"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":[[2024,9,16]]},"DOI":"10.1145\/3652988.3673967","type":"proceedings-article","created":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T12:22:57Z","timestamp":1735215777000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["On LLM Wizards: Identifying Large Language Models' Behaviors for Wizard of Oz Experiments"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9412-4244","authenticated-orcid":false,"given":"Jingchao","family":"Fang","sequence":"first","affiliation":[{"name":"Toyota Research Institute, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5585-7006","authenticated-orcid":false,"given":"Nikos","family":"Arechiga","sequence":"additional","affiliation":[{"name":"Toyota Research Institute, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5519-553X","authenticated-orcid":false,"given":"Keiichi","family":"Namikoshi","sequence":"additional","affiliation":[{"name":"Toyota Research Institute, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9238-9831","authenticated-orcid":false,"given":"Nayeli","family":"Bravo","sequence":"additional","affiliation":[{"name":"Toyota Research Institute, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3240-2560","authenticated-orcid":false,"given":"Candice","family":"Hogan","sequence":"additional","affiliation":[{"name":"Toyota Research Institute, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2399-9374","authenticated-orcid":false,"given":"David A.","family":"Shamma","sequence":"additional","affiliation":[{"name":"Toyota Research Institute, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,26]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1017\/pan.2023.2"},{"key":"e_1_3_2_2_2_1","volume-title":"Constitutional AI: Harmlessness from AI Feedback. arxiv:2212.08073\u00a0[cs.CL]","author":"Bai Yuntao","year":"2022","unstructured":"Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, Carol Chen, Catherine Olsson, Christopher Olah, Danny Hernandez, Dawn Drain, Deep Ganguli, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jamie Kerr, Jared Mueller, Jeffrey Ladish, Joshua Landau, Kamal Ndousse, Kamile Lukosuite, Liane Lovitt, Michael Sellitto, Nelson Elhage, Nicholas Schiefer, Noemi Mercado, Nova DasSarma, Robert Lasenby, Robin Larson, Sam Ringer, Scott Johnston, Shauna Kravec, Sheer\u00a0El Showk, Stanislav Fort, Tamera Lanham, Timothy Telleen-Lawton, Tom Conerly, Tom Henighan, Tristan Hume, Samuel\u00a0R. Bowman, Zac Hatfield-Dodds, Ben Mann, Dario Amodei, Nicholas Joseph, Sam McCandlish, Tom Brown, and Jared Kaplan. 2022. Constitutional AI: Harmlessness from AI Feedback. arxiv:2212.08073\u00a0[cs.CL]"},{"key":"e_1_3_2_2_3_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems 33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877\u20131901."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3312877"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.14236\/ewic\/HCI2017.24"},{"key":"e_1_3_2_2_6_1","unstructured":"Maximillian Chen Weiyan Shi Feifan Yan Ryan Hou Jingwen Zhang Saurav Sahay and Zhou Yu. 2022. Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue. arxiv:2203.07657\u00a0[cs.CL]"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Cheng-Han Chiang and Hung yi Lee. 2023. Can Large Language Models Be an Alternative to Human Evaluations?arxiv:2305.01937\u00a0[cs.CL]","DOI":"10.18653\/v1\/2023.acl-long.870"},{"key":"e_1_3_2_2_8_1","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph\u00a0E. Gonzalez, Ion Stoica, and Eric\u00a0P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/169891.169968"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445924"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2023.04.008"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1056808.1056911"},{"key":"e_1_3_2_2_13_1","volume-title":"The Rating of Chessplayers: Past and Present","author":"Elo A.E.","unstructured":"A.E. Elo. 2008. The Rating of Chessplayers: Past and Present. Ishi Press International, New York, USA."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Xiao Fang Shangkun Che Minjia Mao Hongzhe Zhang Ming Zhao and Xiaohang Zhao. 2023. Bias of AI-Generated Content: An Examination of News Produced by Large Language Models. arxiv:2309.09825\u00a0[cs.AI]","DOI":"10.21203\/rs.3.rs-3499674\/v1"},{"key":"e_1_3_2_2_15_1","volume-title":"A new readability yardstick.Journal of applied psychology 32, 3","author":"Flesch Rudolph","year":"1948","unstructured":"Rudolph Flesch. 1948. A new readability yardstick.Journal of applied psychology 32, 3 (1948), 221."},{"key":"e_1_3_2_2_16_1","volume-title":"A model of similarity-based retrieval. Cognitive science 19, 2","author":"Forbus D","year":"1995","unstructured":"Kenneth\u00a0D Forbus, Dedre Gentner, and Keith Law. 1995. MAC\/FAC: A model of similarity-based retrieval. Cognitive science 19, 2 (1995), 141\u2013205."},{"key":"e_1_3_2_2_17_1","volume-title":"Gptscore: Evaluate as you desire. arXiv preprint arXiv:2302.04166","author":"Fu Jinlan","year":"2023","unstructured":"Jinlan Fu, See-Kiong Ng, Zhengbao Jiang, and Pengfei Liu. 2023. Gptscore: Evaluate as you desire. arXiv preprint arXiv:2302.04166 (2023)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Samuel Gehman Suchin Gururangan Maarten Sap Yejin Choi and Noah\u00a0A. Smith. 2020. RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models. arxiv:2009.11462\u00a0[cs.CL]","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1177\/154193128502900515"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580688"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445569"},{"key":"e_1_3_2_2_22_1","first-page":"1","article-title":"Ai language models cannot replace human research participants","volume":"28","author":"Harding Jacqueline","year":"2023","unstructured":"Jacqueline Harding, William D\u2019Alessandro, NG Laskowski, and Robert Long. 2023. Ai language models cannot replace human research participants. AI & SOCIETY 28, 3 (2023), 1\u20133.","journal-title":"AI & SOCIETY"},{"key":"e_1_3_2_2_23_1","unstructured":"Totte Harinen Alexandre Filipowicz Shabnam Hakimi Rumen Iliev Matthew Klenk and Emily Sumner. 2021. Machine learning reveals how personalized climate communication can both succeed and backfire. arxiv:2109.05104\u00a0[cs.LG]"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sigdial-1.10"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383123"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v8i1.14550"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Boris\u00a0V Janssen Geert Kazemier and Marc\u00a0G Besselink. 2023. The use of ChatGPT and other large language models in surgical science. zrad032\u00a0pages.","DOI":"10.1093\/bjsopen\/zrad032"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581503"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579592"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/800045.801609"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/357417.357420"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300316"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/354401.354406"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581301"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376175"},{"key":"e_1_3_2_2_36_1","volume-title":"Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem.","author":"Li Guohao","year":"2023","unstructured":"Guohao Li, Hasan Abed Al\u00a0Kader Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society. arxiv:2303.17760\u00a0[cs.AI]"},{"key":"e_1_3_2_2_37_1","unstructured":"Shiyang Li Jun Yan Hai Wang Zheng Tang Xiang Ren Vijay Srinivasan and Hongxia Jin. 2023. Instruction-following Evaluation through Verbalizer Manipulation. arxiv:2307.10558\u00a0[cs.CL]"},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of the ACL Workshop: Text Summarization Braches Out. Association for Computational Linguistics","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of summaries. In Proceedings of the ACL Workshop: Text Summarization Braches Out. Association for Computational Linguistics, Barcelona, Spain, 10."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Yang Liu Dan Iter Yichong Xu Shuohang Wang Ruochen Xu and Chenguang Zhu. 2023. G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment. arxiv:2303.16634\u00a0[cs.CL]","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3573861"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/169059.169215"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Nicholas Meade Spandana Gella Devamanyu Hazarika Prakhar Gupta Di Jin Siva Reddy Yang Liu and Dilek Hakkani-T\u00fcr. 2023. Using In-Context Learning to Improve Dialogue Safety. arxiv:2302.00871\u00a0[cs.CL]","DOI":"10.18653\/v1\/2023.findings-emnlp.796"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67744-6_28"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3443446"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12966-021-01224-6"},{"key":"e_1_3_2_2_46_1","unstructured":"OpenAI. 2023. API Reference. https:\/\/platform.openai.com\/docs\/api-reference. Accessed: 2023-11-25."},{"key":"e_1_3_2_2_47_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. Association for Computational Linguistics","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, 311\u2013318."},{"key":"e_1_3_2_2_48_1","volume-title":"Generative Agents: Interactive Simulacra of Human Behavior. arxiv:2304.03442\u00a0[cs.HC]","author":"Park Joon\u00a0Sung","year":"2023","unstructured":"Joon\u00a0Sung Park, Joseph\u00a0C. O\u2019Brien, Carrie\u00a0J. Cai, Meredith\u00a0Ringel Morris, Percy Liang, and Michael\u00a0S. Bernstein. 2023. Generative Agents: Interactive Simulacra of Human Behavior. arxiv:2304.03442\u00a0[cs.HC]"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1237"},{"key":"e_1_3_2_2_50_1","volume-title":"Design thinking","author":"Plattner Hasso","unstructured":"Hasso Plattner, Christoph Meinel, and Ulrich Weinberg. 2009. Design thinking. Springer, Germany."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-0201"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Greg Serapio-Garc\u00eda Mustafa Safdari Cl\u00e9ment Crepy Luning Sun Stephen Fitz Peter Romero Marwa Abdulhai Aleksandra Faust and Maja Matari\u0107. 2023. Personality Traits in Large Language Models. arxiv:2307.00184\u00a0[cs.CL]","DOI":"10.21203\/rs.3.rs-3296728\/v1"},{"key":"e_1_3_2_2_53_1","unstructured":"Murray Shanahan Kyle McDonell and Laria Reynolds. 2023. Role-Play with Large Language Models. arxiv:2305.16367\u00a0[cs.CL]"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1339"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376843"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/1228716.1228733"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/1514095.1514115"},{"key":"e_1_3_2_2_58_1","volume-title":"Proceedings of the International Conference on Information Systems - Bridging the Internet of People, Data, and Things 2018(ICIS 2018","author":"Tavanapour Navid","year":"2018","unstructured":"Navid Tavanapour and Eva A.\u00a0C. Bittner. 2018. Automated Facilitation for Idea Platforms: Design and Evaluation of a Chatbot Prototype. In Proceedings of the International Conference on Information Systems - Bridging the Internet of People, Data, and Things 2018(ICIS 2018), Jan Pries-Heje, Sudha Ram, and Michael Rosemann (Eds.). Association for Information Systems, San Francisco, CA, USA, 9\u00a0pages. https:\/\/aisel.aisnet.org\/icis2018\/general\/Presentations\/8"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173632"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"crossref","unstructured":"Yixin Wan George Pu Jiao Sun Aparna Garimella Kai-Wei Chang and Nanyun Peng. 2023. \"Kelly is a Warm Person Joseph is a Role Model\": Gender Biases in LLM-Generated Reference Letters. arxiv:2310.09219\u00a0[cs.CL]","DOI":"10.18653\/v1\/2023.findings-emnlp.243"},{"key":"e_1_3_2_2_61_1","unstructured":"Peiyi Wang Lei Li Liang Chen Zefan Cai Dawei Zhu Binghuai Lin Yunbo Cao Qi Liu Tianyu Liu and Zhifang Sui. 2023. Large Language Models are not Fair Evaluators. arxiv:2305.17926\u00a0[cs.CL]"},{"key":"e_1_3_2_2_62_1","volume-title":"In Proceedings of the Seventh conference on International Language Resources and Evaluation(LREC \u201910)","author":"Webb Nick","year":"2010","unstructured":"Nick Webb, David Benyon, Jay Bradley, Preben Hansen, and Oli Mival. 2010. Wizard of Oz Experiments for a companion dialogue system: eliciting companionable conversation.. In In Proceedings of the Seventh conference on International Language Resources and Evaluation(LREC \u201910). European Language Resources Association (ELRA), Valletta, Malta, 5\u00a0pages."},{"key":"e_1_3_2_2_63_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_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173662"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1080\/00986283.2010.510976"},{"key":"e_1_3_2_2_66_1","unstructured":"Junchao Wu Shu Yang Runzhe Zhan Yulin Yuan Derek\u00a0F. Wong and Lidia\u00a0S. Chao. 2023. A Survey on LLM-generated Text Detection: Necessity Methods and Future Directions. arxiv:2310.14724\u00a0[cs.CL]"},{"key":"e_1_3_2_2_67_1","unstructured":"Zhaofeng Wu Linlu Qiu Alexis Ross Ekin Aky\u00fcrek Boyuan Chen Bailin Wang Najoung Kim Jacob Andreas and Yoon Kim. 2023. Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks. arxiv:2307.02477\u00a0[cs.CL]"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581252"},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3301275.3302264"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3381804"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025496"},{"key":"e_1_3_2_2_72_1","unstructured":"Shunyu Yao Dian Yu Jeffrey Zhao Izhak Shafran Thomas\u00a0L. Griffiths Yuan Cao and Karthik Narasimhan. 2023. Tree of Thoughts: Deliberate Problem Solving with Large Language Models. arxiv:2305.10601\u00a0[cs.CL]"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1080\/15456870.2020.1808660"},{"key":"e_1_3_2_2_74_1","unstructured":"Zhiyuan Zeng Jiatong Yu Tianyu Gao Yu Meng Tanya Goyal and Danqi Chen. 2023. Evaluating Large Language Models at Evaluating Instruction Following. arxiv:2310.07641\u00a0[cs.CL]"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"crossref","unstructured":"Guanhua Zhang Bing Bai Junqi Zhang Kun Bai Conghui Zhu and Tiejun Zhao. 2020. Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting. arxiv:2004.14088\u00a0[cs.CL]","DOI":"10.18653\/v1\/2020.acl-main.380"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.2196\/22845"},{"key":"e_1_3_2_2_77_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric.\u00a0P Xing Hao Zhang Joseph\u00a0E. Gonzalez and Ion Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. arxiv:2306.05685\u00a0[cs.CL]"},{"key":"e_1_3_2_2_78_1","unstructured":"Kyrie\u00a0Zhixuan Zhou and Madelyn\u00a0Rose Sanfilippo. 2023. Public Perceptions of Gender Bias in Large Language Models: Cases of ChatGPT and Ernie. arxiv:2309.09120\u00a0[cs.AI]"}],"event":{"name":"IVA '24: ACM International Conference on Intelligent Virtual Agents","location":"GLASGOW United Kingdom","acronym":"IVA '24","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence"]},"container-title":["Proceedings of the ACM International Conference on Intelligent Virtual Agents"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652988.3673967","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652988.3673967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:10:47Z","timestamp":1755882647000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652988.3673967"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,16]]},"references-count":78,"alternative-id":["10.1145\/3652988.3673967","10.1145\/3652988"],"URL":"https:\/\/doi.org\/10.1145\/3652988.3673967","relation":{},"subject":[],"published":{"date-parts":[[2024,9,16]]},"assertion":[{"value":"2024-12-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}