{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:02:42Z","timestamp":1750309362944,"version":"3.41.0"},"reference-count":40,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T00:00:00Z","timestamp":1722556800000},"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":["ACM Trans. Recomm. Syst."],"published-print":{"date-parts":[[2025,3,31]]},"abstract":"<jats:p>\n            Conversational critiquing in recommender systems offers a way for users to engage in multi-turn conversations to find items they enjoy. For users to trust an agent and give effective feedback, the recommender system must be able to\n            <jats:italic>explain<\/jats:italic>\n            its suggestions and rationales. We develop a two-part framework for training multi-turn conversational critiquing in recommender systems that provide recommendation rationales that users can effectively interact with to receive better recommendations. First, we train a recommender system to jointly suggest items and explain its reasoning via subjective rationales. We then fine-tune this model to incorporate iterative user feedback via self-supervised bot-play. Experiments on three real-world datasets demonstrate that our system can be applied to different recommendation models across diverse domains to achieve state-of-the-art performance in multi-turn recommendation. Human studies show that systems trained with our framework provide more useful, helpful, and knowledgeable suggestions in warm- and cold-start settings. Our framework allows us to use only product reviews during training, avoiding the need for expensive dialog transcript datasets that limit the applicability of previous conversational recommender agents.\n          <\/jats:p>","DOI":"10.1145\/3665502","type":"journal-article","created":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T08:27:30Z","timestamp":1716280050000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-Supervised Bot Play for Transcript-Free Conversational Critiquing with Rationales"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1503-7351","authenticated-orcid":false,"given":"Shuyang","family":"Li","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, University of California, San Diego, La Jolla, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2691-305X","authenticated-orcid":false,"given":"Bodhisattwa","family":"Prasad Majumder","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Allen Institute for Artificial Intelligence, Seattle, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0955-7588","authenticated-orcid":false,"given":"Julian","family":"McAuley","sequence":"additional","affiliation":[{"name":"Dept of Computer Science and Engineering, University of California, San Diego, La Jolla, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,8,2]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474249"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/72"},{"key":"e_1_3_2_4_2","first-page":"462","volume-title":"AAAI","author":"Burke Robin D.","year":"1996","unstructured":"Robin D. Burke, Kristian J. Hammond, and Benjamin C. Young. 1996. Knowledge-based navigation of complex information spaces. In AAAI. AAAI Press\/The MIT Press, 462\u2013468."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/64.608186"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939746"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/169891.169968"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1177\/001316447303300309"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1203"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00128"},{"key":"e_1_3_2_11_2","first-page":"1","volume-title":"ICLR","author":"Kingma Diederik P.","year":"2014","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-encoding variational Bayes. In ICLR. ICLR, 1\u20139. Retrieved from: http:\/\/arxiv.org\/abs\/1312.6114"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.2307\/2529310"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371769"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403258"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412240"},{"key":"e_1_3_2_17_2","first-page":"1","article-title":"ACUTE-EVAL: Improved dialogue evaluation with optimized questions and multi-turn comparisons","volume":"1909","author":"Li Margaret","year":"2019","unstructured":"Margaret Li, Jason Weston, and Stephen Roller. 2019. ACUTE-EVAL: Improved dialogue evaluation with optimized questions and multi-turn comparisons. CoRR abs\/1909.03087 (2019), 1\u20138.","journal-title":"CoRR"},{"key":"e_1_3_2_18_2","first-page":"9748","volume-title":"NeurIPS","author":"Li Raymond","year":"2018","unstructured":"Raymond Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, and Chris Pal. 2018. Towards deep conversational recommendations. In NeurIPS. NeurIPS, 9748\u20139758."},{"key":"e_1_3_2_19_2","first-page":"1","volume-title":"ICLR","author":"Liu Liyuan","year":"2020","unstructured":"Liyuan Liu, Haoming Jiang, Pengcheng He, Weizhu Chen, Xiaodong Liu, Jianfeng Gao, and Jiawei Han. 2020. On the variance of the adaptive learning rate and beyond. In ICLR. ICLR, 1\u20139."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380003"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401091"},{"key":"e_1_3_2_22_2","first-page":"14786","volume-title":"ICML","author":"Majumder Bodhisattwa Prasad","year":"2022","unstructured":"Bodhisattwa Prasad Majumder, Oana Camburu, Thomas Lukasiewicz, and Julian J. McAuley. 2022. Knowledge-grounded self-rationalization via extractive and natural language explanations. In ICML, Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 14786\u201314801. Retrieved from: https:\/\/proceedings.mlr.press\/v162\/majumder22a.html"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.110"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1018"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2015.01.007"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.2753\/MIS0742-1222250405"},{"key":"e_1_3_2_28_2","first-page":"452","volume-title":"UAI","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In UAI. AUAI Press, 452\u2013461."},{"key":"e_1_3_2_29_2","first-page":"3854","volume-title":"IJCAI","author":"Sedhain Suvash","year":"2016","unstructured":"Suvash Sedhain, Hung Hai Bui, Jaya Kawale, Nikos Vlassis, Branislav Kveton, Aditya Krishna Menon, Trung Bui, and Scott Sanner. 2016. Practical linear models for large-scale one-class collaborative filtering. In IJCAI. IJCAI\/AAAI Press, 3854\u20133860. Retrieved from: http:\/\/www.ijcai.org\/Abstract\/16\/542"},{"key":"e_1_3_2_30_2","article-title":"Distributional contrastive embedding for clarification-based conversational critiquing","author":"Shen Tianshu","year":"2022","unstructured":"Tianshu Shen, Zheda Mai, Ga Wu, and Scott Sanner. 2022. Distributional contrastive embedding for clarification-based conversational critiquing. In WWW. Retrieved from: https:\/\/api.semanticscholar.org\/CorpusID:248367589","journal-title":"WWW"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/506443.506619"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/1639714.1639777"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-85820-3_15"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.5555\/3217144.3217145"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/1502650.1502661"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240369"},{"key":"e_1_3_2_37_2","first-page":"77","volume-title":"Beyond Personalization Workshop","author":"W\u00e4rnest\u00e5l Pontus","year":"2005","unstructured":"Pontus W\u00e4rnest\u00e5l. 2005. Modeling a dialogue strategy for personalized movie recommendations. In Beyond Personalization Workshop. ACM, 77\u201382."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347009"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271776"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609579"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403143"}],"container-title":["ACM Transactions on Recommender Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665502","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3665502","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:03Z","timestamp":1750291563000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665502"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,2]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,3,31]]}},"alternative-id":["10.1145\/3665502"],"URL":"https:\/\/doi.org\/10.1145\/3665502","relation":{},"ISSN":["2770-6699"],"issn-type":[{"type":"electronic","value":"2770-6699"}],"subject":[],"published":{"date-parts":[[2024,8,2]]},"assertion":[{"value":"2023-01-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}