{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T07:12:03Z","timestamp":1766301123362,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":73,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"Tencent","doi-asserted-by":"publisher","award":["Rhino-Bird Focused Research Program"],"award-info":[{"award-number":["Rhino-Bird Focused Research Program"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Impact Fund","award":["No.R1015-23"],"award-info":[{"award-number":["No.R1015-23"]}]},{"name":"Collaborative Research Fund","award":["No.C1043-24GF"],"award-info":[{"award-number":["No.C1043-24GF"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730059","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:21:38Z","timestamp":1752456098000},"page":"1455-1465","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6051-8659","authenticated-orcid":false,"given":"Yuhao","family":"Wang","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2697-7012","authenticated-orcid":false,"given":"Junwei","family":"Pan","sequence":"additional","affiliation":[{"name":"Tencent Inc., Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4712-3676","authenticated-orcid":false,"given":"Pengyue","family":"Jia","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5976-0707","authenticated-orcid":false,"given":"Wanyu","family":"Wang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0073-0172","authenticated-orcid":false,"given":"Maolin","family":"Wang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1519-0227","authenticated-orcid":false,"given":"Zhixiang","family":"Feng","sequence":"additional","affiliation":[{"name":"Tencent Inc., Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7547-8525","authenticated-orcid":false,"given":"Xiaotian","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent Inc., Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9658-5127","authenticated-orcid":false,"given":"Jie","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tencent Inc., Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2926-4416","authenticated-orcid":false,"given":"Xiangyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608857"},{"key":"e_1_3_2_1_2_1","volume-title":"Llm2vec: Large language models are secretly powerful text encoders. arXiv preprint arXiv:2404.05961","author":"BehnamGhader Parishad","year":"2024","unstructured":"Parishad BehnamGhader, Vaibhav Adlakha, Marius Mosbach, Dzmitry Bahdanau, Nicolas Chapados, and Siva Reddy. 2024. Llm2vec: Large language models are secretly powerful text encoders. arXiv preprint arXiv:2404.05961 (2024)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614978"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599922"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688098"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080797"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331254"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672008"},{"key":"e_1_3_2_1_9_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_10_1","volume-title":"Long-Sequence Recommendation Models Need Decoupled Embeddings. arXiv preprint arXiv:2410.02604","author":"Feng Ningya","year":"2024","unstructured":"Ningya Feng, Junwei Pan, Jialong Wu, Baixu Chen, Ximei Wang, Qian Li, Xian Hu, Jie Jiang, and Mingsheng Long. 2024. Long-Sequence Recommendation Models Need Decoupled Embeddings. arXiv preprint arXiv:2410.02604 (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Yufei Feng Fuyu Lv Weichen Shen Menghan Wang Fei Sun Yu Zhu and Keping Yang. 2019. Deep session interest network for click-through rate prediction. In IJCAI.","DOI":"10.24963\/ijcai.2019\/319"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/1005332.1005335"},{"key":"e_1_3_2_1_13_1","volume-title":"Characteristic kernels on groups and semigroups. Advances in neural information processing systems","author":"Fukumizu Kenji","year":"2008","unstructured":"Kenji Fukumizu, Arthur Gretton, Bernhard Sch\u00f6lkopf, and Bharath K Sriperumbudur. 2008. Characteristic kernels on groups and semigroups. Advances in neural information processing systems, Vol. 21 (2008)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637871"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/2503308.2188410"},{"key":"e_1_3_2_1_16_1","volume-title":"Optimal kernel choice for large-scale two-sample tests. Advances in neural information processing systems","author":"Gretton Arthur","year":"2012","unstructured":"Arthur Gretton, Dino Sejdinovic, Heiko Strathmann, Sivaraman Balakrishnan, Massimiliano Pontil, Kenji Fukumizu, and Bharath K Sriperumbudur. 2012b. Optimal kernel choice for large-scale two-sample tests. Advances in neural information processing systems, Vol. 25 (2012)."},{"key":"e_1_3_2_1_17_1","volume-title":"On the Embedding Collapse when Scaling up Recommendation Models. ICML","author":"Guo Xingzhuo","year":"2024","unstructured":"Xingzhuo Guo, Junwei Pan, Ximei Wang, Baixu Chen, Jie Jiang, and Mingsheng Long. 2024. On the Embedding Collapse when Scaling up Recommendation Models. ICML (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648589"},{"key":"e_1_3_2_1_20_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_21_1","unstructured":"Bal\u00e1zs Hidasi Alexandros Karatzoglou Linas Baltrunas and Domonkos Tikk. 2016. SESSION-BASED RECOMMENDATIONS WITH RECURRENT NEURAL NETWORKS. In ICLR."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"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","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/30.1-2.81"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608779"},{"key":"e_1_3_2_1_26_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023b. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730--19742."},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on machine learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_28_1","volume-title":"CTRL: Connect Collaborative and Language Model for CTR Prediction. arXiv preprint arXiv:2306.02841","author":"Li Xiangyang","year":"2023","unstructured":"Xiangyang Li, Bo Chen, Lu Hou, and Ruiming Tang. 2023a. CTRL: Connect Collaborative and Language Model for CTR Prediction. arXiv preprint arXiv:2306.02841 (2023)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583378"},{"key":"e_1_3_2_1_30_1","volume-title":"Llara: Aligning large language models with sequential recommenders. arXiv preprint arXiv:2312.02445","author":"Liao Jiayi","year":"2023","unstructured":"Jiayi Liao, Sihang Li, Zhengyi Yang, Jiancan Wu, Yancheng Yuan, Xiang Wang, and Xiangnan He. 2023. Llara: Aligning large language models with sequential recommenders. arXiv preprint arXiv:2312.02445 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Crocodile: Cross Experts Covariance for Disentangled Learning in Multi-Domain Recommendation. arXiv preprint arXiv:2405.12706","author":"Lin Zhutian","year":"2024","unstructured":"Zhutian Lin, Junwei Pan, Haibin Yu, Xi Xiao, Ximei Wang, Zhixiang Feng, Shifeng Wen, Shudong Huang, Lei Xiao, and Jie Jiang. 2024. Crocodile: Cross Experts Covariance for Disentangled Learning in Multi-Domain Recommendation. arXiv preprint arXiv:2405.12706 (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350953"},{"key":"e_1_3_2_1_33_1","first-page":"26701","article-title":"Llm-esr: Large language models enhancement for long-tailed sequential recommendation","volume":"37","author":"Liu Qidong","year":"2024","unstructured":"Qidong Liu, Xian Wu, Yejing Wang, Zijian Zhang, Feng Tian, Yefeng Zheng, and Xiangyu Zhao. 2024b. Llm-esr: Large language models enhancement for long-tailed sequential recommendation. Advances in Neural Information Processing Systems, Vol. 37 (2024), 26701--26727.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","volume-title":"An Aligning and Training Framework for Multimodal Recommendations. arXiv preprint arXiv:2403.12384","author":"Liu Yifan","year":"2024","unstructured":"Yifan Liu, Kangning Zhang, Xiangyuan Ren, Yanhua Huang, Jiarui Jin, Yingjie Qin, Ruilong Su, Ruiwen Xu, and Weinan Zhang. 2024c. An Aligning and Training Framework for Multimodal Recommendations. arXiv preprint arXiv:2403.12384 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657829"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583467"},{"key":"e_1_3_2_1_37_1","unstructured":"Ilya Loshchilov Frank Hutter et al. 2017. Fixing weight decay regularization in adam. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2488200"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781680832891"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1018"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671607"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412744"},{"key":"e_1_3_2_1_43_1","volume-title":"Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Tran, Jonah Samost, et al.","author":"Rajput Shashank","year":"2024","unstructured":"Shashank Rajput, Nikhil Mehta, Anima Singh, Raghunandan Hulikal Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Tran, Jonah Samost, et al. 2024. Recommender systems with generative retrieval. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Equivalence of distance-based and RKHS-based statistics in hypothesis testing. The annals of statistics","author":"Sejdinovic Dino","year":"2013","unstructured":"Dino Sejdinovic, Bharath Sriperumbudur, Arthur Gretton, and Kenji Fukumizu. 2013. Equivalence of distance-based and RKHS-based statistics in hypothesis testing. The annals of statistics (2013), 2263--2291."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680068"},{"key":"e_1_3_2_1_46_1","unstructured":"Zihua Si Lin Guan ZhongXiang Sun Xiaoxue Zang Jing Lu Yiqun Hui Xingchao Cao Zeyu Yang Yichen Zheng Dewei Leng et al. 2024. TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishou. arXiv preprint arXiv:2407.16357 (2024)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688190"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28749"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_1_51_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_52_1","volume-title":"FLIP: Towards Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction. arXiv e-prints","author":"Wang Hangyu","year":"2023","unstructured":"Hangyu Wang, Jianghao Lin, Xiangyang Li, Bo Chen, Chenxu Zhu, Ruiming Tang, Weinan Zhang, and Yong Yu. 2023b. FLIP: Towards Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction. arXiv e-prints (2023), arXiv--2310."},{"key":"e_1_3_2_1_53_1","volume-title":"Rethinking large language model architectures for sequential recommendations. arXiv preprint arXiv:2402.09543","author":"Wang Hanbing","year":"2024","unstructured":"Hanbing Wang, Xiaorui Liu, Wenqi Fan, Xiangyu Zhao, Venkataramana Kini, Devendra Yadav, Fei Wang, Zhen Wen, Jiliang Tang, and Hui Liu. 2024a. Rethinking large language model architectures for sequential recommendations. arXiv preprint arXiv:2402.09543 (2024)."},{"key":"e_1_3_2_1_54_1","volume-title":"Yi Wong, Ziru Liu, Xiangyu Zhao, Yichao Wang, Bo Chen, Huifeng Guo, and Ruiming Tang.","author":"Wang Yuhao","year":"2023","unstructured":"Yuhao Wang, Ha Tsz Lam, Yi Wong, Ziru Liu, Xiangyu Zhao, Yichao Wang, Bo Chen, Huifeng Guo, and Ruiming Tang. 2023a. Multi-task deep recommender systems: A survey. arXiv preprint arXiv:2302.03525 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635807"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679743"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591750"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.331"},{"key":"e_1_3_2_1_60_1","unstructured":"Derong Xu Ziheng Zhang Zhenxi Lin Xian Wu Zhihong Zhu Tong Xu Xiangyu Zhao Yefeng Zheng and Enhong Chen. 2024. Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models. In LREC\/COLING."},{"key":"e_1_3_2_1_61_1","unstructured":"Xihong Yang Heming Jing Zixing Zhang Jindong Wang Huakang Niu Shuaiqiang Wang Yu Lu Junfeng Wang Dawei Yin Xinwang Liu et al. 2024. DaRec: A Disentangled Alignment Framework for Large Language Model and Recommender System. arXiv preprint arXiv:2408.08231 (2024)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591932"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557348"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00067"},{"key":"e_1_3_2_1_65_1","volume-title":"Towards Scalable Semantic Representation for Recommendation. arXiv preprint arXiv:2410.09560","author":"Zhang Taolin","year":"2024","unstructured":"Taolin Zhang, Junwei Pan, Jinpeng Wang, Yaohua Zha, Bin Chen, Shengshui Luo, Yuan Wang, Ming Yue, Jie Jiang, and Shu-Tao Xia. 2024b. Towards Scalable Semantic Representation for Recommendation. arXiv preprint arXiv:2410.09560 (2024)."},{"key":"e_1_3_2_1_66_1","volume-title":"Collm: Integrating collaborative embeddings into large language models for recommendation. arXiv preprint arXiv:2310.19488","author":"Zhang Yang","year":"2023","unstructured":"Yang Zhang, Fuli Feng, Jizhi Zhang, Keqin Bao, Qifan Wang, and Xiangnan He. 2023. Collm: Integrating collaborative embeddings into large language models for recommendation. arXiv preprint arXiv:2310.19488 (2023)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557461"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00118"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"crossref","unstructured":"Guorui Zhou Na Mou Ying Fan Qi Pi Weijie Bian Chang Zhou Xiaoqiang Zhu and Kun Gai. 2019. Deep interest evolution network for click-through rate prediction. In AAAI. 5941--5948.","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"crossref","unstructured":"Guorui Zhou Xiaoqiang Zhu Chenru Song Ying Fan Han Zhu Xiao Ma Yanghui Yan Junqi Jin Han Li and Kun Gai. 2018. Deep interest network for click-through rate prediction. In SIGKDD. 1059--1068.","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_1_73_1","volume-title":"Temporal Interest Network for User Response Prediction. In Companion Proceedings of the ACM on Web Conference","author":"Zhou Haolin","year":"2024","unstructured":"Haolin Zhou, Junwei Pan, Xinyi Zhou, Xihua Chen, Jie Jiang, Xiaofeng Gao, and Guihai Chen. 2024. Temporal Interest Network for User Response Prediction. In Companion Proceedings of the ACM on Web Conference 2024. 413--422."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Padua Italy","acronym":"SIGIR '25"},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T10:01:12Z","timestamp":1755856872000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730059"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":73,"alternative-id":["10.1145\/3726302.3730059","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730059","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}