{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:08Z","timestamp":1784179088410,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"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":[[2025,3,10]]},"DOI":"10.1145\/3701551.3703496","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T12:30:16Z","timestamp":1740573016000},"page":"107-116","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Large Language Model driven Policy Exploration for Recommender Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7117-8580","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"first","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6063-9023","authenticated-orcid":false,"given":"Alexandros","family":"Karatzoglou","sequence":"additional","affiliation":[{"name":"Amazon, Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2528-6597","authenticated-orcid":false,"given":"Ioannis","family":"Arapakis","sequence":"additional","affiliation":[{"name":"Telefonica Research, Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9228-1759","authenticated-orcid":false,"given":"Joemon M.","family":"Jose","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Tallrec: An effective and efficient tuning framework to align large language model with recommendation. arXiv preprint arXiv:2305.00447","author":"Bao Keqin","year":"2023","unstructured":"Keqin Bao, Jizhi Zhang, Yang Zhang, Wenjie Wang, Fuli Feng, and Xiangnan He. 2023. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. arXiv preprint arXiv:2305.00447 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Jin Chen Zheng Liu Xu Huang Chenwang Wu Qi Liu Gangwei Jiang Yuanhao Pu Yuxuan Lei Xiaolong Chen Xingmei Wang et al. 2023. When large language models meet personalization: Perspectives of challenges and opportunities. arXiv preprint arXiv:2307.16376 (2023).","DOI":"10.1007\/s11280-024-01276-1"},{"key":"e_1_3_2_1_3_1","volume-title":"Enhancing job recommendation through llm-based generative adversarial networks. arXiv preprint arXiv:2307.10747","author":"Du Yingpeng","year":"2023","unstructured":"Yingpeng Du, Di Luo, Rui Yan, Hongzhi Liu, Yang Song, Hengshu Zhu, and Jie Zhang. 2023. Enhancing job recommendation through llm-based generative adversarial networks. arXiv preprint arXiv:2307.10747 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Recommender systems in the era of large language models (llms). arXiv preprint arXiv:2307.02046","author":"Fan Wenqi","year":"2023","unstructured":"Wenqi Fan, Zihuai Zhao, Jiatong Li, Yunqing Liu, Xiaowei Mei, Yiqi Wang, Jiliang Tang, and Qing Li. 2023. Recommender systems in the era of large language models (llms). arXiv preprint arXiv:2307.02046 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 23rd International Conference on Neural Information Processing Systems -","volume":"1","author":"Farahmand Amir","year":"2010","unstructured":"Amir massoud Farahmand, R\u00e9mi Munos, and Csaba Szepesv\u00e1ri. 2010. Error propagation for Approximate Policy and Value Iteration. In Proceedings of the 23rd International Conference on Neural Information Processing Systems - Volume 1 (Vancouver, British Columbia, Canada) (NIPS'10). Curran Associates Inc., Red Hook, NY, USA, 568--576."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635805"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546767"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412214"},{"key":"e_1_3_2_1_9_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614949"},{"key":"e_1_3_2_1_11_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539381"},{"key":"e_1_3_2_1_13_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_14_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_16_1","volume-title":"Actor-critic algorithms. Advances in neural information processing systems","author":"Konda Vijay","year":"1999","unstructured":"Vijay Konda and John Tsitsiklis. 1999. Actor-critic algorithms. Advances in neural information processing systems, Vol. 12 (1999)."},{"key":"e_1_3_2_1_17_1","volume-title":"Algorithms for multi-armed bandit problems. arXiv preprint arXiv:1402.6028","author":"Kuleshov Volodymyr","year":"2014","unstructured":"Volodymyr Kuleshov and Doina Precup. 2014. Algorithms for multi-armed bandit problems. arXiv preprint arXiv:1402.6028 (2014)."},{"key":"e_1_3_2_1_18_1","volume-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","author":"Kumar Aviral","unstructured":"Aviral Kumar, Justin Fu, George Tucker, and Sergey Levine. 2019. Stabilizing off-policy Q-learning via bootstrapping error reduction. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_2_1_19_1","volume-title":"Reward Design with Language Models. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=10uNUgI5Kl","author":"Kwon Minae","year":"2023","unstructured":"Minae Kwon, Sang Michael Xie, Kalesha Bullard, and Dorsa Sadigh. 2023. Reward Design with Language Models. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=10uNUgI5Kl"},{"key":"e_1_3_2_1_20_1","volume-title":"Annual Conference on Robot Learning.","author":"Lee Seunghyun","year":"2021","unstructured":"Seunghyun Lee, Younggyo Seo, Kimin Lee, Pieter Abbeel, and Jinwoo Shin. 2021. Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble. In Annual Conference on Robot Learning."},{"key":"e_1_3_2_1_21_1","volume-title":"Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971","author":"Lillicrap Timothy P","year":"2015","unstructured":"Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)."},{"key":"e_1_3_2_1_22_1","unstructured":"Jianghao Lin Xinyi Dai Yunjia Xi Weiwen Liu Bo Chen Xiangyang Li Chenxu Zhu Huifeng Guo Yong Yu Ruiming Tang et al. 2023. How Can Recommender Systems Benefit from Large Language Models: A Survey. arXiv preprint arXiv:2306.05817 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583244"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"e_1_3_2_1_26_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1018"},{"key":"e_1_3_2_1_28_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, Vol. 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_30_1","unstructured":"Shashank Rajput Nikhil Mehta Anima Singh Raghunandan H Keshavan Trung Vu Lukasz Heldt Lichan Hong Yi Tay Vinh Q Tran Jonah Samost et al. 2023. Recommender Systems with Generative Retrieval. arXiv preprint arXiv:2305.05065 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591656"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20783"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912004"},{"key":"e_1_3_2_1_34_1","volume-title":"international conference on machine learning. PMLR, 1670--1679","author":"Schnabel Tobias","year":"2016","unstructured":"Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, and Thorsten Joachims. 2016. Recommendations as treatments: Debiasing learning and evaluation. In international conference on machine learning. PMLR, 1670--1679."},{"key":"e_1_3_2_1_35_1","volume-title":"International Conference on Machine Learning. PMLR, 9443--9454","author":"Seo Younggyo","year":"2021","unstructured":"Younggyo Seo, Lili Chen, Jinwoo Shin, Honglak Lee, Pieter Abbeel, and Kimin Lee. 2021. State entropy maximization with random encoders for efficient exploration. In International Conference on Machine Learning. PMLR, 9443--9454."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657683"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_1_38_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv: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, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657767"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679533"},{"key":"e_1_3_2_1_41_1","volume-title":"Transrec: Learning transferable recommendation from mixture-of-modality feedback. arXiv preprint arXiv:2206.06190","author":"Wang Jie","year":"2022","unstructured":"Jie Wang, Fajie Yuan, Mingyue Cheng, Joemon M Jose, Chenyun Yu, Beibei Kong, Xiangnan He, Zhijin Wang, Bo Hu, and Zang Li. 2022. Transrec: Learning transferable recommendation from mixture-of-modality feedback. arXiv preprint arXiv:2206.06190 (2022)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401134"},{"key":"e_1_3_2_1_43_1","volume-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning","author":"Williams Ronald J","year":"1992","unstructured":"Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, Vol. 8 (1992), 229--256."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401147"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498494"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531714"},{"key":"e_1_3_2_1_47_1","volume-title":"EasyRL4Rec: A User-Friendly Code Library for Reinforcement Learning Based Recommender Systems. arXiv preprint arXiv:2402.15164","author":"Yu Yuanqing","year":"2024","unstructured":"Yuanqing Yu, Chongming Gao, Jiawei Chen, Heng Tang, Yuefeng Sun, Qian Chen, Weizhi Ma, and Min Zhang. 2024. EasyRL4Rec: A User-Friendly Code Library for Reinforcement Learning Based Recommender Systems. arXiv preprint arXiv:2402.15164 (2024)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290975"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608885"},{"key":"e_1_3_2_1_50_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"}],"event":{"name":"WSDM '25: The Eighteenth ACM International Conference on Web Search and Data Mining","location":"Hannover Germany","acronym":"WSDM '25","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 Eighteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3703496","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701551.3703496","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T09:05:34Z","timestamp":1755767134000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3703496"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":51,"alternative-id":["10.1145\/3701551.3703496","10.1145\/3701551"],"URL":"https:\/\/doi.org\/10.1145\/3701551.3703496","relation":{},"subject":[],"published":{"date-parts":[[2025,3,10]]},"assertion":[{"value":"2025-03-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}