{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T21:45:12Z","timestamp":1782251112288,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"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":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679792","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:21Z","timestamp":1729452861000},"page":"3135-3144","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Reformulating Conversational Recommender Systems as Tri-Phase Offline Policy Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4092-993X","authenticated-orcid":false,"given":"Gangyi","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5187-9196","authenticated-orcid":false,"given":"Chongming","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8020-203X","authenticated-orcid":false,"given":"Hang","family":"Pan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2628-1558","authenticated-orcid":false,"given":"Runzhe","family":"Teng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6816-5302","authenticated-orcid":false,"given":"Ruizhe","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Chen Qibin","year":"1803","unstructured":"Qibin Chen, Junyang Lin, Yichang Zhang, Ming Ding, Yukuo Cen, Hongxia Yang, and Jie Tang. 2019. Towards Knowledge-Based Recommender Dialog System. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan (Eds.). Association for Computational Linguistics, Hong Kong, China, 1803--1813."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","author":"Christakopoulou Konstantina","unstructured":"Konstantina Christakopoulou, Alex Beutel, Rui Li, Sagar Jain, and Ed H. Chi. 2018. Q&R: A Two-Stage Approach toward Interactive Recommendation. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (London, United Kingdom) (KDD '18). Association for Computing Machinery, New York, NY, USA, 139--148."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939746"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570443"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657755"},{"key":"e_1_3_2_1_6_1","volume-title":"SIGIR Forum","volume":"56","author":"Deffayet Romain","year":"2023","unstructured":"Romain Deffayet, Thibaut Thonet, Jean-Michel Renders, and Maarten de Rijke. 2023. Offline Evaluation for Reinforcement Learning-Based Recommendation: A Critical Issue and Some Alternatives. SIGIR Forum, Vol. 56, 2, Article 3 (jan 2023), 14 pages."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462913"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657843"},{"key":"e_1_3_2_1_9_1","unstructured":"Luke Friedman Sameer Ahuja David Allen Zhenning Tan Hakim Sidahmed Changbo Long Jun Xie Gabriel Schubiner Ajay Patel Harsh Lara et al. 2023. Leveraging large language models in conversational recommender systems. arXiv preprint arXiv:2305.07961 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591636"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.06.002"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557220"},{"key":"e_1_3_2_1_13_1","article-title":"CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System","volume":"42","author":"Gao Chongming","year":"2023","unstructured":"Chongming Gao, Shiqi Wang, Shijun Li, Jiawei Chen, Xiangnan He, Wenqiang Lei, Biao Li, Yuan Zhang, and Peng Jiang. 2023. CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System. ACM Trans. Inf. Syst., Vol. 42, 1, Article 14 (aug 2023), 27 pages.","journal-title":"ACM Trans. Inf. Syst."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371769"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403258"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327546.3327641"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3446427"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3008563"},{"key":"e_1_3_2_1_19_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657683"},{"key":"e_1_3_2_1_21_1","volume-title":"Conversational Recommender System. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","author":"Sun Yueming","year":"2018","unstructured":"Yueming Sun and Yi Zhang. 2018. Conversational Recommender System. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval (Ann Arbor, MI, USA) (SIGIR '18). Association for Computing Machinery, New York, NY, USA, 235--244."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330989"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.621"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3155900"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531714"},{"key":"e_1_3_2_1_27_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yang Zhengyi","year":"2024","unstructured":"Zhengyi Yang, Jiancan Wu, Zhicai Wang, Xiang Wang, Yancheng Yuan, and Xiangnan He. 2024. Generate what you prefer: Reshaping sequential recommendation via guided diffusion. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657868"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608885"},{"key":"e_1_3_2_1_30_1","volume-title":"Adaptive Vague Preference Policy Learning for Multi-round Conversational Recommendation. arXiv preprint arXiv:2306.04487","author":"Zhang Gangyi","year":"2023","unstructured":"Gangyi Zhang, Chongming Gao, Wenqiang Lei, Xiaojie Guo, Shijun Li, Hongshen Chen, Zhuozhi Ding, Sulong Xu, and Lingfei Wu. 2023. Adaptive Vague Preference Policy Learning for Multi-round Conversational Recommendation. arXiv preprint arXiv:2306.04487 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403202"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512088"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403143"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679792","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679792","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:28Z","timestamp":1750294708000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679792"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":33,"alternative-id":["10.1145\/3627673.3679792","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679792","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}