{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:48:10Z","timestamp":1784821690365,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"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":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657767","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"375-385","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["Reinforcement Learning-based Recommender Systems with Large Language Models for State Reward and Action Modeling"],"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":[[2024,7,11]]},"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":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_4_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_5_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_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","volume-title":"Language Models Represent Space and Time. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=jE8xbmvFin","author":"Gurnee Wes","year":"2024","unstructured":"Wes Gurnee and Max Tegmark. 2024. Language Models Represent Space and Time. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=jE8xbmvFin"},{"key":"e_1_3_2_1_9_1","volume-title":"Advances in neural information processing systems","author":"Hasselt Hado","year":"2010","unstructured":"Hado Hasselt. 2010. Double Q-learning. Advances in neural information processing systems, Vol. 23 (2010)."},{"key":"e_1_3_2_1_10_1","volume-title":"Sparseadapter: An easy approach for improving the parameter-efficiency of adapters. arXiv preprint arXiv:2210.04284","author":"He Shwai","year":"2022","unstructured":"Shwai He, Liang Ding, Daize Dong, Miao Zhang, and Dacheng Tao. 2022. Sparseadapter: An easy approach for improving the parameter-efficiency of adapters. arXiv preprint arXiv:2210.04284 (2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614949"},{"key":"e_1_3_2_1_12_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_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401225"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539381"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Machine Learning. PMLR, 2790--2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790--2799."},{"key":"e_1_3_2_1_16_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_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219846"},{"key":"e_1_3_2_1_18_1","volume-title":"Lidong Bing, and Soujanya Poria.","author":"Hu Zhiqiang","year":"2023","unstructured":"Zhiqiang Hu, Yihuai Lan, Lei Wang, Wanyu Xu, Ee-Peng Lim, Roy Ka-Wei Lee, Lidong Bing, and Soujanya Poria. 2023. LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models. arXiv preprint arXiv:2304.01933 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"How to Index Item IDs for Recommendation Foundation Models. arXiv preprint arXiv:2305.06569","author":"Hua Wenyue","year":"2023","unstructured":"Wenyue Hua, Shuyuan Xu, Yingqiang Ge, and Yongfeng Zhang. 2023. How to Index Item IDs for Recommendation Foundation Models. arXiv preprint arXiv:2305.06569 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_22_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_23_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=DeG07_TcZvT","author":"Li Kenneth","year":"2023","unstructured":"Kenneth Li, Aspen K Hopkins, David Bau, Fernanda Vi\u00e9gas, Hanspeter Pfister, and Martin Wattenberg. 2023a. Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=DeG07_TcZvT"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615017"},{"key":"e_1_3_2_1_25_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_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_1_27_1","volume-title":"Zhengxiao Du, Zhilin Yang, and Jie Tang.","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Kaixuan Ji, Yicheng Fu, Weng Lam Tam, Zhengxiao Du, Zhilin Yang, and Jie Tang. 2021. P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:2110.07602 (2021)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2365952.2365971"},{"key":"e_1_3_2_1_30_1","volume-title":"Sentence-t5: Scalable sentence encoders from pre-trained text-to-text models. arXiv preprint arXiv:2108.08877","author":"Ni Jianmo","year":"2021","unstructured":"Jianmo Ni, Gustavo Hern\u00e1ndez \u00c1brego, Noah Constant, Ji Ma, Keith B Hall, Daniel Cer, and Yinfei Yang. 2021. Sentence-t5: Scalable sentence encoders from pre-trained text-to-text models. arXiv preprint arXiv:2108.08877 (2021)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1018"},{"key":"e_1_3_2_1_32_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_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_34_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_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591656"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912004"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498471"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_1_39_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_40_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_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401134"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401147"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498494"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531714"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290975"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290975"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608885"},{"key":"e_1_3_2_1_48_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_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657767","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:34:13Z","timestamp":1755840853000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657767"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":49,"alternative-id":["10.1145\/3626772.3657767","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657767","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}