{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T08:17:08Z","timestamp":1786090628566,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":87,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2427070, IIS-2331069, IIS-2202481, IIS-2130263, CNS-2131622"],"award-info":[{"award-number":["CNS-2427070, IIS-2331069, IIS-2202481, IIS-2130263, CNS-2131622"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737088","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:03:27Z","timestamp":1754255007000},"page":"3692-3703","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Preference-Optimized Retrieval and Ranking for Efficient Multimodal Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0309-2065","authenticated-orcid":false,"given":"Zhenrui","family":"Yue","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0198-2352","authenticated-orcid":false,"given":"Huimin","family":"Zeng","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1374-7082","authenticated-orcid":false,"given":"Yueqi","family":"Wang","sequence":"additional","affiliation":[{"name":"UC Berkley, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0955-7588","authenticated-orcid":false,"given":"Julian","family":"McAuley","sequence":"additional","affiliation":[{"name":"UC San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9599-8023","authenticated-orcid":false,"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716-23736.","DOI":"10.52202\/068431-1723"},{"key":"e_1_3_2_1_2_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_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.42122"},{"key":"e_1_3_2_1_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_5_1","volume-title":"PALR: Personalization Aware LLMs for Recommendation. arXiv preprint arXiv:2305.07622","author":"Chen Zheng","year":"2023","unstructured":"Zheng Chen. 2023. PALR: Personalization Aware LLMs for Recommendation. arXiv preprint arXiv:2305.07622 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Charles Sutton, Sebastian Gehrmann, et al.","author":"Chowdhery Aakanksha","year":"2022","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al., 2022. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)."},{"key":"e_1_3_2_1_7_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2024","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi. 2024. Instructblip: Towards general-purpose vision-language models with instruction tuning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691","author":"Dao Tri","year":"2023","unstructured":"Tri Dao. 2023. Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Qlora: Efficient finetuning of quantized llms. arXiv preprint arXiv:2305.14314","author":"Dettmers Tim","year":"2023","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. Qlora: Efficient finetuning of quantized llms. arXiv preprint arXiv:2305.14314 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota."},{"key":"e_1_3_2_1_11_1","volume-title":"User Embedding Model for Personalized Language Prompting. arXiv preprint arXiv:2401.04858","author":"Doddapaneni Sumanth","year":"2024","unstructured":"Sumanth Doddapaneni, Krishna Sayana, Ambarish Jash, Sukhdeep Sodhi, and Dima Kuzmin. 2024. User Embedding Model for Personalized Language Prompting. arXiv preprint arXiv:2401.04858 (2024)."},{"key":"e_1_3_2_1_12_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_13_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. 2023. Chat-rec: Towards interactive and explainable llms-augmented recommender system. arXiv preprint arXiv:2303.14524 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546767"},{"key":"e_1_3_2_1_15_1","volume-title":"VIP5: Towards Multimodal Foundation Models for Recommendation. arXiv preprint arXiv:2305.14302","author":"Geng Shijie","year":"2023","unstructured":"Shijie Geng, Juntao Tan, Shuchang Liu, Zuohui Fu, and Yongfeng Zhang. 2023. VIP5: Towards Multimodal Foundation Models for Recommendation. arXiv preprint arXiv:2305.14302 (2023)."},{"key":"e_1_3_2_1_16_1","unstructured":"Shangmin Guo Biao Zhang Tianlin Liu Tianqi Liu Misha Khalman Felipe Llinares Alexandre Rame Thomas Mesnard Yao Zhao Bilal Piot et al. 2024. Direct language model alignment from online ai feedback. arXiv preprint arXiv:2402.04792 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3610639"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883037"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482136"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3551468"},{"key":"e_1_3_2_1_22_1","volume-title":"Reference-free monolithic preference optimization with odds ratio. arXiv e-prints","author":"Hong Jiwoo","year":"2024","unstructured":"Jiwoo Hong, Noah Lee, and James Thorne. 2024. Reference-free monolithic preference optimization with odds ratio. arXiv e-prints (2024), arXiv-2403."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583434"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539381"},{"key":"e_1_3_2_1_25_1","volume-title":"Large language models are zero-shot rankers for recommender systems. arXiv preprint arXiv:2305.08845","author":"Hou Yupeng","year":"2023","unstructured":"Yupeng Hou, Junjie Zhang, Zihan Lin, Hongyu Lu, Ruobing Xie, Julian McAuley, and Wayne Xin Zhao. 2023b. Large language models are zero-shot rankers for recommender systems. arXiv preprint arXiv:2305.08845 (2023)."},{"key":"e_1_3_2_1_26_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_27_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"MANTIS: Interleaved Multi-Image Instruction Tuning. arXiv preprint arXiv:2405.01483","author":"Jiang Dongfu","year":"2024","unstructured":"Dongfu Jiang, Xuan He, Huaye Zeng, Cong Wei, Max Ku, Qian Liu, and Wenhu Chen. 2024. MANTIS: Interleaved Multi-Image Instruction Tuning. arXiv preprint arXiv:2405.01483 (2024)."},{"key":"e_1_3_2_1_29_1","unstructured":"Bowen Jin Hansi Zeng Guoyin Wang Xiusi Chen Tianxin Wei Ruirui Li Zhengyang Wang Zheng Li Yang Li Hanqing Lu et al. 2023. Language Models As Semantic Indexers. arXiv preprint arXiv:2310.07815 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_31_1","volume-title":"Chi, and Derek Zhiyuan Cheng","author":"Kang Wang-Cheng","year":"2023","unstructured":"Wang-Cheng Kang, Jianmo Ni, Nikhil Mehta, Maheswaran Sathiamoorthy, Lichan Hong, Ed Chi, and Derek Zhiyuan Cheng. 2023. Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction. arXiv preprint arXiv:2305.06474 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/322217.322232"},{"key":"e_1_3_2_1_33_1","volume-title":"What matters when building vision-language models? arXiv preprint arXiv:2405.02246","author":"Lauren\u00e7on Hugo","year":"2024","unstructured":"Hugo Lauren\u00e7on, L\u00e9o Tronchon, Matthieu Cord, and Victor Sanh. 2024. What matters when building vision-language models? arXiv preprint arXiv:2405.02246 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"Text Is All You Need: Learning Language Representations for Sequential Recommendation. arXiv preprint arXiv:2305.13731","author":"Li Jiacheng","year":"2023","unstructured":"Jiacheng Li, Ming Wang, Jin Li, Jinmiao Fu, Xin Shen, Jingbo Shang, and Julian McAuley. 2023b. Text Is All You Need: Learning Language Representations for Sequential Recommendation. arXiv preprint arXiv:2305.13731 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"GPT4Rec: A generative framework for personalized recommendation and user interests interpretation. arXiv preprint arXiv:2304.03879","author":"Li Jinming","year":"2023","unstructured":"Jinming Li, Wentao Zhang, Tian Wang, Guanglei Xiong, Alan Lu, and Gerard Medioni. 2023d. GPT4Rec: A generative framework for personalized recommendation and user interests interpretation. arXiv preprint arXiv:2304.03879 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615017"},{"key":"e_1_3_2_1_37_1","volume-title":"E4SRec: An Elegant Effective Efficient Extensible Solution of Large Language Models for Sequential Recommendation. arXiv preprint arXiv:2312.02443","author":"Li Xinhang","year":"2023","unstructured":"Xinhang Li, Chong Chen, Xiangyu Zhao, Yong Zhang, and Chunxiao Xing. 2023a. E4SRec: An Elegant Effective Efficient Extensible Solution of Large Language Models for Sequential Recommendation. arXiv preprint arXiv:2312.02443 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657690"},{"key":"e_1_3_2_1_39_1","volume-title":"Ra-dit: Retrieval-augmented dual instruction tuning. arXiv preprint arXiv:2310.01352","author":"Lin Xi Victoria","year":"2023","unstructured":"Xi Victoria Lin, Xilun Chen, Mingda Chen, Weijia Shi, Maria Lomeli, Rich James, Pedro Rodriguez, Jacob Kahn, Gergely Szilvasy, Mike Lewis, et al., 2023. Ra-dit: Retrieval-augmented dual instruction tuning. arXiv preprint arXiv:2310.01352 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"A Practice-Friendly Two-Stage LLM-Enhanced Paradigm in Sequential Recommendation. arXiv preprint arXiv:2406.00333","author":"Liu Dugang","year":"2024","unstructured":"Dugang Liu, Shenxian Xian, Xiaolin Lin, Xiaolian Zhang, Hong Zhu, Yuan Fang, Zhen Chen, and Zhong Ming. 2024b. A Practice-Friendly Two-Stage LLM-Enhanced Paradigm in Sequential Recommendation. arXiv preprint arXiv:2406.00333 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"Visual instruction tuning. arXiv preprint arXiv:2304.08485","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_43_1","volume-title":"Rec-GPT4V: Multimodal Recommendation with Large Vision-Language Models. arXiv preprint arXiv:2402.08670","author":"Liu Yuqing","year":"2024","unstructured":"Yuqing Liu, Yu Wang, Lichao Sun, and Philip S Yu. 2024a. Rec-GPT4V: Multimodal Recommendation with Large Vision-Language Models. arXiv preprint arXiv:2402.08670 (2024)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531378"},{"key":"e_1_3_2_1_45_1","volume-title":"RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation. arXiv preprint arXiv:2312.16018","author":"Luo Sichun","year":"2023","unstructured":"Sichun Luo, Bowei He, Haohan Zhao, Yinya Huang, Aojun Zhou, Zongpeng Li, Yuanzhang Xiao, Mingjie Zhan, and Linqi Song. 2023. RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation. arXiv preprint arXiv:2312.16018 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380130"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_1_48_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. ArXiv Vol. abs\/2303.08774 (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"Resurrecting recurrent neural networks for long sequences. arXiv preprint arXiv:2303.06349","author":"Orvieto Antonio","year":"2023","unstructured":"Antonio Orvieto, Samuel L Smith, Albert Gu, Anushan Fernando, Caglar Gulcehre, Razvan Pascanu, and Soham De. 2023. Resurrecting recurrent neural networks for long sequences. arXiv preprint arXiv:2303.06349 (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","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.","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_2_1_51_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_52_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_53_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_54_1","first-page":"10299","article-title":"Recommender systems with generative retrieval","volume":"36","author":"Rajput Shashank","year":"2023","unstructured":"Shashank Rajput, Nikhil Mehta, Anima Singh, Raghunandan Hulikal Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Tran, Jonah Samost, et al., 2023. Recommender systems with generative retrieval. Advances in Neural Information Processing Systems, Vol. 36 (2023), 10299-10315.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_55_1","volume-title":"International Conference on Machine Learning. PMLR, 8821-8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning. PMLR, 8821-8831."},{"key":"e_1_3_2_1_56_1","unstructured":"Machel Reid Nikolay Savinov Denis Teplyashin Dmitry Lepikhin Timothy Lillicrap Jean-baptiste Alayrac Radu Soricut Angeliki Lazaridou Orhan Firat Julian Schrittwieser et al. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)."},{"key":"e_1_3_2_1_57_1","volume-title":"Representation learning with large language models for recommendation. arXiv preprint arXiv:2310.15950","author":"Ren Xubin","year":"2023","unstructured":"Xubin Ren, Wei Wei, Lianghao Xia, Lixin Su, Suqi Cheng, Junfeng Wang, Dawei Yin, and Chao Huang. 2023. Representation learning with large language models for recommendation. arXiv preprint arXiv:2310.15950 (2023)."},{"key":"e_1_3_2_1_58_1","unstructured":"Adam Roberts Colin Raffel Katherine Lee Michael Matena Noam Shazeer Peter J Liu Sharan Narang Wei Li and Yanqi Zhou. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. (2019)."},{"key":"e_1_3_2_1_59_1","volume-title":"Fran\u00e7ois Yvon, Matthias Gall\u00e9, et al.","author":"Scao Teven Le","year":"2022","unstructured":"Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Fran\u00e7ois Yvon, Matthias Gall\u00e9, et al., 2022. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)."},{"key":"e_1_3_2_1_60_1","volume-title":"RoFormer: enhanced transformer with rotary position embedding. CoRR abs\/2104.09864","author":"Su Jianlin","year":"2021","unstructured":"Jianlin Su, Yu Lu, Shengfeng Pan, Bo Wen, and Yunfeng Liu. 2021. RoFormer: enhanced transformer with rotary position embedding. CoRR abs\/2104.09864 (2021). arXiv preprint arXiv:2104.09864 (2021)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411947"},{"key":"e_1_3_2_1_63_1","volume-title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent. arXiv preprint arXiv:2304.09542","author":"Sun Weiwei","year":"2023","unstructured":"Weiwei Sun, Lingyong Yan, Xinyu Ma, Pengjie Ren, Dawei Yin, and Zhaochun Ren. 2023. Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent. arXiv preprint arXiv:2304.09542 (2023)."},{"key":"e_1_3_2_1_64_1","volume-title":"Siamak Shakeri, Dara Bahri","author":"Tay Yi","year":"2022","unstructured":"Yi Tay, Mostafa Dehghani, Vinh Q Tran, Xavier Garcia, Jason Wei, Xuezhi Wang, Hyung Won Chung, Siamak Shakeri, Dara Bahri, Tal Schuster, et al., 2022. Ul2: Unifying language learning paradigms. arXiv preprint arXiv:2205.05131 (2022)."},{"key":"e_1_3_2_1_65_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_66_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_67_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_68_1","volume-title":"Recmind: Large language model powered agent for recommendation. arXiv preprint arXiv:2308.14296","author":"Wang Yancheng","year":"2023","unstructured":"Yancheng Wang, Ziyan Jiang, Zheng Chen, Fan Yang, Yingxue Zhou, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, and Yingzhen Yang. 2023. Recmind: Large language model powered agent for recommendation. arXiv preprint arXiv:2308.14296 (2023)."},{"key":"e_1_3_2_1_69_1","volume-title":"Train Once","author":"Wang Yueqi","year":"2024","unstructured":"Yueqi Wang, Zhenrui Yue, Huimin Zeng, Dong Wang, and Julian McAuley. 2024b. Train Once, Deploy Anywhere: Matryoshka Representation Learning for Multimodal Recommendation. arXiv preprint arXiv:2409.16627 (2024)."},{"key":"e_1_3_2_1_70_1","volume-title":"Zihang Dai, Yulia Tsvetkov, and Yuan Cao.","author":"Wang Zirui","year":"2021","unstructured":"Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, and Yuan Cao. 2021. Simvlm: Simple visual language model pretraining with weak supervision. arXiv preprint arXiv:2108.10904 (2021)."},{"key":"e_1_3_2_1_71_1","unstructured":"Tianxin Wei Bowen Jin Ruirui Li Hansi Zeng Zhengyang Wang Jianhui Sun Qingyu Yin Hanqing Lu Suhang Wang Jingrui He et al. 2024a. Towards unified multi-modal personalization: Large vision-language models for generative recommendation and beyond. arXiv preprint arXiv:2403.10667 (2024)."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583206"},{"key":"e_1_3_2_1_73_1","volume-title":"Llmrec: Large language models with graph augmentation for recommendation.","author":"Wei Wei","year":"2024","unstructured":"Wei Wei, Xubin Ren, Jiabin Tang, Qinyong Wang, Lixin Su, Suqi Cheng, Junfeng Wang, Dawei Yin, and Chao Huang. 2024b. Llmrec: Large language models with graph augmentation for recommendation. (2024), 806-815."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671901"},{"key":"e_1_3_2_1_75_1","volume-title":"Wayne Xin Zhao, and Ji-Rong Wen","author":"Xu Lanling","year":"2024","unstructured":"Lanling Xu, Junjie Zhang, Bingqian Li, Jinpeng Wang, Mingchen Cai, Wayne Xin Zhao, and Ji-Rong Wen. 2024. Prompting Large Language Models for Recommender Systems: A Comprehensive Framework and Empirical Analysis. arXiv preprint arXiv:2401.04997 (2024)."},{"key":"e_1_3_2_1_76_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang et al. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)."},{"key":"e_1_3_2_1_77_1","volume-title":"Harnessing multimodal large language models for multimodal sequential recommendation. arXiv preprint arXiv:2408.09698","author":"Ye Yuyang","year":"2024","unstructured":"Yuyang Ye, Zhi Zheng, Yishan Shen, Tianshu Wang, Hengruo Zhang, Peijun Zhu, Runlong Yu, Kai Zhang, and Hui Xiong. 2024. Harnessing multimodal large language models for multimodal sequential recommendation. arXiv preprint arXiv:2408.09698 (2024)."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474275"},{"key":"e_1_3_2_1_79_1","volume-title":"Dong Wang, and Even Oldridge.","author":"Yue Zhenrui","year":"2023","unstructured":"Zhenrui Yue, Sara Rabhi, Gabriel de Souza Pereira Moreira, Dong Wang, and Even Oldridge. 2023a. LlamaRec: Two-stage recommendation using large language models for ranking. arXiv preprint arXiv:2311.02089 (2023)."},{"key":"e_1_3_2_1_80_1","volume-title":"Linear Recurrent Units for Sequential Recommendation. arXiv preprint arXiv:2310.02367","author":"Yue Zhenrui","year":"2023","unstructured":"Zhenrui Yue, Yueqi Wang, Zhankui He, Huimin Zeng, Julian McAuley, and Dong Wang. 2023b. Linear Recurrent Units for Sequential Recommendation. arXiv preprint arXiv:2310.02367 (2023)."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"e_1_3_2_1_82_1","volume-title":"Leyu Lin, and Ji-Rong Wen.","author":"Zhang Junjie","year":"2023","unstructured":"Junjie Zhang, Ruobing Xie, Yupeng Hou, Wayne Xin Zhao, Leyu Lin, and Ji-Rong Wen. 2023. Recommendation as instruction following: A large language model empowered recommendation approach. arXiv preprint arXiv:2305.07001 (2023)."},{"key":"e_1_3_2_1_83_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al., 2022b. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_84_1","volume-title":"Machine Learning for Healthcare Conference. PMLR, 2-25","author":"Zhang Yuhao","year":"2022","unstructured":"Yuhao Zhang, Hang Jiang, Yasuhide Miura, Christopher D Manning, and Curtis P Langlotz. 2022a. Contrastive learning of medical visual representations from paired images and text. In Machine Learning for Healthcare Conference. PMLR, 2-25."},{"key":"e_1_3_2_1_85_1","volume-title":"Wayne Xin Zhao, and Ji-Rong Wen","author":"Zheng Bowen","year":"2023","unstructured":"Bowen Zheng, Yupeng Hou, Hongyu Lu, Yu Chen, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Adapting large language models by integrating collaborative semantics for recommendation. arXiv preprint arXiv:2311.09049 (2023)."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512111"},{"key":"e_1_3_2_1_87_1","volume-title":"A setwise approach for effective and highly efficient zero-shot ranking with large language models. arXiv preprint arXiv:2310.09497","author":"Zhuang Shengyao","year":"2023","unstructured":"Shengyao Zhuang, Honglei Zhuang, Bevan Koopman, and Guido Zuccon. 2023. A setwise approach for effective and highly efficient zero-shot ranking with large language models. arXiv preprint arXiv:2310.09497 (2023)."}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:54:21Z","timestamp":1777571661000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737088"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":87,"alternative-id":["10.1145\/3711896.3737088","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737088","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}