{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:29Z","timestamp":1786120829906,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFF0725001"],"award-info":[{"award-number":["2023YFF0725001"]}]},{"name":"National Natural Science Foundation of China","award":["92370204"],"award-info":[{"award-number":["92370204"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2023B1515120057"],"award-info":[{"award-number":["2023B1515120057"]}]},{"name":"Key-Area Special Project of Guangdong Provincial Ordinary Universities","award":["2024ZDZX1007"],"award-info":[{"award-number":["2024ZDZX1007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818318","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"8267-8278","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Aligning Large Language Models with Searcher Preferences"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1590-601X","authenticated-orcid":false,"given":"Wei","family":"Wu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Data Science, University of Science and Technology of China, HeFei, AnHui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6407-6571","authenticated-orcid":false,"given":"Peilun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2166-4386","authenticated-orcid":false,"given":"Liyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9715-836X","authenticated-orcid":false,"given":"Qimeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8192-8246","authenticated-orcid":false,"given":"Chengqiang","family":"Lu","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc., Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5960-1684","authenticated-orcid":false,"given":"Yan","family":"Gao","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8838-2785","authenticated-orcid":false,"given":"Yi","family":"Wu","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1274-7111","authenticated-orcid":false,"given":"Yao","family":"Hu","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6016-6465","authenticated-orcid":false,"given":"Hui","family":"Xiong","sequence":"additional","affiliation":[{"name":"Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Zheng Cai Maosong Cao Haojiong Chen et al. 2024. InternLM2 Technical Report. arXiv:2403.17297 [cs.CL] https:\/\/arxiv.org\/abs\/2403.17297"},{"key":"e_1_3_2_2_2_1","unstructured":"ChatGPT. 2026. ChatGPT. https:\/\/chatgpt.com\/"},{"key":"e_1_3_2_2_3_1","unstructured":"Ben Chen Xian Guo Siyuan Wang Zihan Liang Yue Lv Yufei Ma Xinlong Xiao Bowen Xue Xuxin Zhang Ying Yang Huangyu Dai Xing Xu Tong Zhao Mingcan Peng Xiaoyang Zheng Chao Wang Qihang Zhao Zhixin Zhai Yang Zhao Bochao Liu Jingshan Lv Xiao Liang Yuqing Ding Jing Chen Chenyi Lei Wenwu Ou Han Li and Kun Gai. 2025. OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Search. arXiv:2509.03236 [cs.IR] https:\/\/arxiv.org\/abs\/2509.03236"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3794"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1189"},{"key":"e_1_3_2_2_7_1","unstructured":"Douyin. [n.d.]. Douyin AI Search. https:\/\/search.douyin.com\/"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/01972240490507974"},{"key":"e_1_3_2_2_9_1","volume-title":"Retrieval-Augmented Generation for Large Language Models: A Survey. ArXiv abs\/2312.10997","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Qianyu Guo, Meng Wang, and Haofen Wang. 2023. Retrieval-Augmented Generation for Large Language Models: A Survey. ArXiv abs\/2312.10997 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266359151"},{"key":"e_1_3_2_2_10_1","unstructured":"Gemini. 2026. Gemini. https:\/\/gemini.google.com\/"},{"key":"e_1_3_2_2_11_1","volume-title":"Sam Toyer, Johannes Heidecke, Alex Beutel, and Amelia Glaese.","author":"Guan Melody Y.","year":"2025","unstructured":"Melody Y. Guan, Manas Joglekar, Eric Wallace, Saachi Jain, Boaz Barak, Alec Helyar, Rachel Dias, Andrea Vallone, Hongyu Ren, Jason Wei, Hyung Won Chung, Sam Toyer, Johannes Heidecke, Alex Beutel, and Amelia Glaese. 2025. Deliberative Alignment: Reasoning Enables Safer Language Models. arXiv:2412.16339 [cs.CL] https:\/\/arxiv.org\/abs\/2412.16339"},{"key":"e_1_3_2_2_12_1","unstructured":"Anisha Gunjal Anthony Wang Elaine Lau Vaskar Nath Yunzhong He Bing Liu and Sean Hendryx. 2025. Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains. arXiv:2507.17746 [cs.LG] https:\/\/arxiv.org\/abs\/2507.17746"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"e_1_3_2_2_14_1","volume-title":"Sujan Gonugondla, Hunter Lang, Yue Yu, Yundi Qian, Maryam Fazel-Zarandi, Licheng Yu, Amine Benhalloum, Hany Awadalla, and Manaal Faruqui.","author":"He Yun","year":"2025","unstructured":"Yun He, Wenzhe Li, Hejia Zhang, Songlin Li, Karishma Mandyam, Sopan Khosla, Yuanhao Xiong, Nanshu Wang, Xiaoliang Peng, Beibin Li, Shengjie Bi, Shishir G. Patil, Qi Qi, Shengyu Feng, Julian Katz-Samuels, Richard Yuanzhe Pang, Sujan Gonugondla, Hunter Lang, Yue Yu, Yundi Qian, Maryam Fazel-Zarandi, Licheng Yu, Amine Benhalloum, Hany Awadalla, and Manaal Faruqui. 2025. AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following. arXiv:2511.10507 [cs.CL] https:\/\/arxiv.org\/abs\/2511.10507"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"26901","author":"Lee Harrison","year":"2024","unstructured":"Harrison Lee, Samrat Phatale, Hassan Mansoor, Thomas Mesnard, Johan Ferret, Kellie Ren Lu, Colton Bishop, Ethan Hall, Victor Carbune, Abhinav Rastogi, and Sushant Prakash. 2024. RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback. In Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 26874-26901. https:\/\/proceedings.mlr.press\/v235\/lee24t.html"},{"key":"e_1_3_2_2_17_1","volume-title":"Abbas Ghaddar, Qianyi Sun, Liheng Ma, Yu Luo, Dong Li, Mark Coates, Jianye Hao, and Yingxue Zhang.","author":"Li Derek","year":"2025","unstructured":"Derek Li, Jiaming Zhou, Leo Maxime Brunswic, Abbas Ghaddar, Qianyi Sun, Liheng Ma, Yu Luo, Dong Li, Mark Coates, Jianye Hao, and Yingxue Zhang. 2025. Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling. arXiv:2507.14783 [cs.LG] https:\/\/arxiv.org\/abs\/2507.14783"},{"key":"e_1_3_2_2_18_1","unstructured":"Zhiding Liu Ben Chen Mingyue Cheng Enhong Chen Li Li Chenyi Lei Wenwu Ou Han Li and Kun Gai. 2025. Towards Context-aware Reasoning-enhanced Generative Searching in E-commerce. arXiv:2510.16925 [cs.IR] https:\/\/arxiv.org\/abs\/2510.16925"},{"key":"e_1_3_2_2_19_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_2_2_20_1","volume-title":"Rafael Rafailov, Chase Blagden, Nathan Lile, Louis Castricato, Jan-Philipp Fr\u00e4nken, Chelsea Finn, and Alon Albalak.","author":"Mahan Dakota","year":"2024","unstructured":"Dakota Mahan, Duy Van Phung, Rafael Rafailov, Chase Blagden, Nathan Lile, Louis Castricato, Jan-Philipp Fr\u00e4nken, Chelsea Finn, and Alon Albalak. 2024. Generative Reward Models. arXiv:2410.12832 [cs.LG] https:\/\/arxiv.org\/abs\/2410.12832"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.20944\/preprints202604.0428.v3"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_2_23_1","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2020. Passage Re-ranking with BERT. arXiv:1901.04085 [cs.IR] https:\/\/arxiv.org\/abs\/1901.04085"},{"key":"e_1_3_2_2_24_1","first-page":"27730","volume-title":"Oh (Eds.)","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, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F Christiano, Jan Leike, and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 27730-27744. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/b1efde53be364a73914f58805a001731-Paper-Conference.pdf"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Ming Pang Chunyuan Yuan Xiaoyu He Zheng Fang Donghao Xie Fanyi Qu Xue Jiang Changping Peng Zhangang Lin Ching Law and Jingping Shao. 2025. Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval. arXiv:2504.01403 [cs.IR] https:\/\/arxiv.org\/abs\/2504.01403","DOI":"10.1145\/3701716.3715228"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3648298"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.97"},{"key":"e_1_3_2_2_28_1","first-page":"53728","volume-title":"Levine (Eds.)","volume":"36","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 53728-53741. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/a85b405ed65c6477a4fe8302b5e06ce7-Paper-Conference.pdf"},{"key":"e_1_3_2_2_29_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arXiv:1707.06347 [cs.LG] https:\/\/arxiv.org\/abs\/1707.06347"},{"key":"e_1_3_2_2_30_1","unstructured":"Zhihong Shao Peiyi Wang Qihao Zhu Runxin Xu Junxiao Song Xiao Bi Haowei Zhang Mingchuan Zhang Y. K. Li Y. Wu and Daya Guo. 2024. DeepSeek-Math: Pushing the Limits of Mathematical Reasoning in Open Language Models. arXiv:2402.03300 [cs.CL] https:\/\/arxiv.org\/abs\/2402.03300"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696075"},{"key":"e_1_3_2_2_32_1","unstructured":"Siddharth Suri Scott Counts Leijie Wang Chacha Chen Mengting Wan Tara Safavi Jennifer Neville Chirag Shah Ryen W. White Reid Andersen Georg Buscher Sathish Manivannan Nagu Rangan and Longqi Yang. 2024. The Use of Generative Search Engines for Knowledge Work and Complex Tasks. arXiv:2404.04268 [cs.IR] https:\/\/arxiv.org\/abs\/2404.04268"},{"key":"e_1_3_2_2_33_1","unstructured":"TikTok. 2026. TikTok. https:\/\/www.tiktok.com\/"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.410"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Vijay Viswanathan Yanchao Sun Shuang Ma Xiang Kong Meng Cao Graham Neubig and Tongshuang Wu. 2025. Checklists Are Better Than Reward Models For Aligning Language Models. arXiv:2507.18624 [cs.CL] https:\/\/arxiv.org\/abs\/2507.18624","DOI":"10.52202\/085713-3824"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.585"},{"key":"e_1_3_2_2_37_1","unstructured":"WeChat. 2026. WeChat. https:\/\/www.wechat.com\/"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Wei Wu Liyi Chen Congxi Xiao Tianfu Wang Qimeng Wang Chengqiang Lu Yan Gao Yi Wu Yao Hu and Hui Xiong. 2026. Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models. arXiv:2601.03969 [cs.AI] https:\/\/arxiv.org\/abs\/2601.03969","DOI":"10.18653\/v1\/2026.acl-long.1047"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737138"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657724"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3451185"},{"key":"e_1_3_2_2_42_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv Chujie Zheng Dayiheng Liu Fan Zhou Fei Huang Feng Hu Hao Ge Haoran Wei Huan Lin Jialong Tang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Yang Jiaxi Yang Jing Zhou Jingren Zhou Junyang Lin Kai Dang Keqin Bao Kexin Yang Le Yu Lianghao Deng Mei Li Mingfeng Xue Mingze Li Pei Zhang Peng Wang Qin Zhu Rui Men Ruize Gao Shixuan Liu Shuang Luo Tianhao Li Tianyi Tang Wenbiao Yin Xingzhang Ren Xinyu Wang Xinyu Zhang Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yinger Zhang Yu Wan Yuqiong Liu Zekun Wang Zeyu Cui Zhenru Zhang Zhipeng Zhou and Zihan Qiu. 2025. Qwen3 Technical Report. arXiv:2505.09388 [cs.CL] https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"e_1_3_2_2_43_1","unstructured":"Zheng Yuan Hongyi Yuan Chengpeng Li Guanting Dong Keming Lu Chuanqi Tan Chang Zhou and Jingren Zhou. 2023. Scaling Relationship on Learning Mathematical Reasoning with Large Language Models. arXiv:2308.01825 [cs.CL] https:\/\/arxiv.org\/abs\/2308.01825"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645477"},{"key":"e_1_3_2_2_45_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Ccwp4tFEtE","author":"Zhang Lunjun","year":"2025","unstructured":"Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, and Rishabh Agarwal. 2025. Generative Verifiers: Reward Modeling as Next-Token Prediction. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Ccwp4tFEtE"},{"key":"e_1_3_2_2_46_1","first-page":"46595","volume-title":"Levine (Eds.)","volume":"36","author":"Zheng Lianmin","year":"2023","unstructured":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, Hao Zhang, Joseph E Gonzalez, and Ion Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 46595-46623. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/91f18a1287b398d378ef22505bf41832-Paper-Datasets_and_Benchmarks.pdf"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3748304"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:29:26Z","timestamp":1786066166000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818318"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":47,"alternative-id":["10.1145\/3770855.3818318","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818318","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}