{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T21:00:19Z","timestamp":1770757219221,"version":"3.50.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Anhui Provincial Natural Science Foundation","award":["2408085QF189"],"award-info":[{"award-number":["2408085QF189"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402470, 62272437, U24B20180, 62121002"],"award-info":[{"award-number":["62402470, 62272437, U24B20180, 62121002"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Central Universities of China","award":["WK2100000053, PA2024GDSK0107"],"award-info":[{"award-number":["WK2100000053, PA2024GDSK0107"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0111802"],"award-info":[{"award-number":["2021ZD0111802"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20241643"],"award-info":[{"award-number":["GZC20241643"]}]},{"name":"Advanced computing resources provided by the Supercomputing Center of the USTC"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,28]]},"DOI":"10.1145\/3696410.3714524","type":"proceedings-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T22:47:11Z","timestamp":1745362031000},"page":"5075-5084","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["SPRec: Self-Play to Debias LLM-based Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5187-9196","authenticated-orcid":false,"given":"Chongming","family":"Gao","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0186-9561","authenticated-orcid":false,"given":"Ruijun","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6730-5755","authenticated-orcid":false,"given":"Shuai","family":"Yuan","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4868-0952","authenticated-orcid":false,"given":"Kexin","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2942-1576","authenticated-orcid":false,"given":"Yuanqing","family":"Yu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8472-7992","authenticated-orcid":false,"given":"Xiangnan","family":"He","sequence":"additional","affiliation":[{"name":"MoE Key Lab of BIPC, University of Science and Technology of China, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Artificial Intelligence and Statistics (AISTATS '24)","author":"Azar Mohammad Gheshlaghi","year":"2024","unstructured":"Mohammad Gheshlaghi Azar, Zhaohan Daniel Guo, Bilal Piot, Remi Munos, Mark Rowland, Michal Valko, and Daniele Calandriello. 2024. A general theoretical paradigm to understand learning from human preferences. In International Conference on Artificial Intelligence and Statistics (AISTATS '24). PMLR, 4447--4455."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679611"},{"key":"e_1_3_2_1_3_1","volume-title":"A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems. ACM Transactions on Recommender Systems (TORS)","author":"Bao Keqin","year":"2025","unstructured":"Keqin Bao, Jizhi Zhang, Wenjie Wang, Yang Zhang, Zhengyi Yang, Yanchen Luo, Chong Chen, Fuli Feng, and Qi Tian. 2025. A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems. ACM Transactions on Recommender Systems (TORS) (2025)."},{"key":"e_1_3_2_1_4_1","volume-title":"Decoding Matters: Addressing Amplification Bias and Homogeneity Issue for LLM-based Recommendation. EMNLP","author":"Bao Keqin","year":"2024","unstructured":"Keqin Bao, Jizhi Zhang, Yang Zhang, Xinyue Huo, Chong Chen, and Fuli Feng. 2024. Decoding Matters: Addressing Amplification Bias and Homogeneity Issue for LLM-based Recommendation. EMNLP (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"FLOW: A Feedback LOop FrameWork for Simultaneously Enhancing Recommendation and User Agents. arXiv preprint arXiv:2410.20027","author":"Cai Shihao","year":"2024","unstructured":"Shihao Cai, Jizhi Zhang, Keqin Bao, Chongming Gao, and Fuli Feng. 2024. FLOW: A Feedback LOop FrameWork for Simultaneously Enhancing Recommendation and User Agents. arXiv preprint arXiv:2410.20027 (2024)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3692281"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3522672"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3564284"},{"key":"e_1_3_2_1_9_1","volume-title":"DLCRec: A Novel Approach for Managing Diversity in LLM-Based Recommender Systems. The 18th ACM International Conference on Web Search and Data Mining (WSDM '25)","author":"Chen Jiaju","year":"2025","unstructured":"Jiaju Chen, Chongming Gao, Shuai Yuan, Shuchang Liu, Qingpeng Cai, and Peng Jiang. 2025. DLCRec: A Novel Approach for Managing Diversity in LLM-Based Recommender Systems. The 18th ACM International Conference on Web Search and Data Mining (WSDM '25) (2025)."},{"key":"e_1_3_2_1_10_1","volume-title":"On Softmax Direct Preference Optimization for Recommendation. In The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS '24)","author":"Chen Yuxin","year":"2024","unstructured":"Yuxin Chen, Junfei Tan, An Zhang, Zhengyi Yang, Leheng Sheng, Enzhi Zhang, Xiang Wang, and Tat-Seng Chua. 2024b. On Softmax Direct Preference Optimization for Recommendation. In The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS '24)."},{"key":"e_1_3_2_1_11_1","volume-title":"Forty-first International Conference on Machine Learning (ICML '24)","author":"Chen Zixiang","year":"2024","unstructured":"Zixiang Chen, Yihe Deng, Huizhuo Yuan, Kaixuan Ji, and Quanquan Gu. 2024a. Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models. In Forty-first International Conference on Machine Learning (ICML '24)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671458"},{"key":"e_1_3_2_1_13_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective. arXiv preprint arXiv:2404.04626","author":"Feng Duanyu","year":"2024","unstructured":"Duanyu Feng, Bowen Qin, Chen Huang, Zheng Zhang, and Wenqiang Lei. 2024. Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective. arXiv preprint arXiv:2404.04626 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00524"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591636"},{"key":"e_1_3_2_1_17_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. 2023c. CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System. ACM Transactions on Information Systems (TOIS), Vol. 42, 1, Article 14 (aug 2023), 27 pages.","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"e_1_3_2_1_18_1","volume-title":"Chat-rec: Towards interactive and explainable llms-augmented recommender system. arXiv preprint arXiv:2303.14524","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Tao Sheng, Youlin Xiang, Yun Xiong, Haofen Wang, and Jiawei Zhang. 2023b. Chat-rec: Towards interactive and explainable llms-augmented recommender system. arXiv preprint arXiv:2303.14524 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657974"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_24"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS '23)","author":"Jagadeesan Meena","year":"2024","unstructured":"Meena Jagadeesan, Nikhil Garg, and Jacob Steinhardt. 2024. Supply-side equilibria in recommender systems. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS '23). Article 642, 12 pages."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3648158"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_24_1","article-title":"Fairness in Recommendation: Foundations, Methods, and Applications","volume":"14","author":"Li Yunqi","year":"2023","unstructured":"Yunqi Li, Hanxiong Chen, Shuyuan Xu, Yingqiang Ge, Juntao Tan, Shuchang Liu, and Yongfeng Zhang. 2023. Fairness in Recommendation: Foundations, Methods, and Applications. ACM Transactions on Intelligent Systems and Technology (TIST), Vol. 14, 5, Article 95 (Oct. 2023), 48 pages.","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"e_1_3_2_1_25_1","volume-title":"RosePO: Aligning LLM-based Recommenders with Human Values. arXiv preprint arXiv:2410.12519","author":"Liao Jiayi","year":"2024","unstructured":"Jiayi Liao, Xiangnan He, Ruobing Xie, Jiancan Wu, Yancheng Yuan, Xingwu Sun, Zhanhui Kang, and Xiang Wang. 2024. RosePO: Aligning LLM-based Recommenders with Human Values. arXiv preprint arXiv:2410.12519 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"Large Language Models Enhanced Sequential Recommendation for Long-tail User and Item. Advances in Neural Information Processing Systems (NeurIPS)","author":"Liu Qidong","year":"2024","unstructured":"Qidong Liu, Xian Wu, Xiangyu Zhao, Yejing Wang, Zijian Zhang, Feng Tian, and Yefeng Zheng. 2024. Large Language Models Enhanced Sequential Recommendation for Long-tail User and Item. Advances in Neural Information Processing Systems (NeurIPS) (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Reinforced Prompt Personalization for Recommendation with Large Language Models. ACM Transactions on Information Systems (TOIS)","author":"Mao Wenyu","year":"2024","unstructured":"Wenyu Mao, Jiancan Wu, Weijian Chen, Chongming Gao, Xiang Wang, and Xiangnan He. 2024. Reinforced Prompt Personalization for Recommendation with Large Language Models. ACM Transactions on Information Systems (TOIS) (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"Entropy Controllable Direct Preference Optimization. arXiv preprint arXiv:2411.07595","author":"Omura Motoki","year":"2024","unstructured":"Motoki Omura, Yasuhiro Fujita, and Toshiki Kataoka. 2024. Entropy Controllable Direct Preference Optimization. arXiv preprint arXiv:2411.07595 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Smaug: Fixing failure modes of preference optimisation with dpo-positive. arXiv preprint arXiv:2402.13228","author":"Pal Arka","year":"2024","unstructured":"Arka Pal, Deep Karkhanis, Samuel Dooley, Manley Roberts, Siddartha Naidu, and Colin White. 2024. Smaug: Fixing failure modes of preference optimisation with dpo-positive. arXiv preprint arXiv:2402.13228 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Iterative Reasoning Preference Optimization. Advances in Neural Information Processing Systems (NeurIPS)","author":"Pang Richard Yuanzhe","year":"2024","unstructured":"Richard Yuanzhe Pang, Weizhe Yuan, Kyunghyun Cho, He He, Sainbayar Sukhbaatar, and Jason Weston. 2024. Iterative Reasoning Preference Optimization. Advances in Neural Information Processing Systems (NeurIPS) (2024)."},{"key":"e_1_3_2_1_31_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Rafailov Rafael","year":"2024","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2024. Direct preference optimization: Your language model is secretly a reward model. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583223"},{"key":"e_1_3_2_1_33_1","volume-title":"Science","volume":"362","author":"Silver David","year":"2018","unstructured":"David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, and Demis Hassabis. 2018. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science, Vol. 362, 6419 (2018), 1140--1144."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"David Silver Julian Schrittwieser Karen Simonyan Ioannis Antonoglou Aja Huang Arthur Guez Thomas Hubert Lucas Baker Matthew Lai Adrian Bolton et al. 2017. Mastering the game of go without human knowledge. nature Vol. 550 7676 (2017) 354--359.","DOI":"10.1038\/nature24270"},{"key":"e_1_3_2_1_35_1","volume-title":"Inverse-RLignment: Inverse Reinforcement Learning from Demonstrations for LLM Alignment. arXiv preprint arXiv:2405.15624","author":"Sun Hao","year":"2024","unstructured":"Hao Sun and Mihaela van der Schaar. 2024. Inverse-RLignment: Inverse Reinforcement Learning from Demonstrations for LLM Alignment. arXiv preprint arXiv:2405.15624 (2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688182"},{"key":"e_1_3_2_1_37_1","volume-title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints. In The Twelfth International Conference on Learning Representations (ICLR '24)","author":"Wang Chaoqi","year":"2024","unstructured":"Chaoqi Wang, Yibo Jiang, Chenghao Yang, Han Liu, and Yuxin Chen. 2024a. Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints. In The Twelfth International Conference on Learning Representations (ICLR '24)."},{"key":"e_1_3_2_1_38_1","volume-title":"Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond. arXiv preprint arXiv:2410.19744","author":"Wang Qi","year":"2024","unstructured":"Qi Wang, Jindong Li, Shiqi Wang, Qianli Xing, Runliang Niu, He Kong, Rui Li, Guodong Long, Yi Chang, and Chengqi Zhang. 2024b. Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond. arXiv preprint arXiv:2410.19744 (2024)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3547333"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635853"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-024-01291-2"},{"key":"e_1_3_2_1_42_1","volume-title":"Self-Play Preference Optimization for Language Model Alignment. In The Thirteenth International Conference on Learning Representations (ICLR '2025)","author":"Wu Yue","year":"2025","unstructured":"Yue Wu, Zhiqing Sun, Huizhuo Yuan, Kaixuan Ji, Yiming Yang, and Quanquan Gu. 2025. Self-Play Preference Optimization for Language Model Alignment. In The Thirteenth International Conference on Learning Representations (ICLR '2025)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.467"},{"key":"e_1_3_2_1_44_1","volume-title":"Unveiling User Satisfaction and Creator Productivity Trade-Offs in Recommendation Platforms. Advances in Neural Information Processing Systems (NeurIPS)","author":"Yao Fan","year":"2024","unstructured":"Fan Yao, Yiming Liao, Jingzhou Liu, Shaoliang Nie, Qifan Wang, Haifeng Xu, and Hongning Wang. 2024. Unveiling User Satisfaction and Creator Productivity Trade-Offs in Recommendation Platforms. Advances in Neural Information Processing Systems (NeurIPS) (2024)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608860"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645537"}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714524","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714524","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:33Z","timestamp":1750295913000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714524"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":46,"alternative-id":["10.1145\/3696410.3714524","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714524","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}