{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:17:48Z","timestamp":1775841468323,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792806","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"7933-7942","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Aligning Query Rewriting with Human Cognition and Preference in E-Commerce Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6190-1466","authenticated-orcid":false,"given":"Ruize","family":"Ou","sequence":"first","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9385-4624","authenticated-orcid":false,"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1179-004X","authenticated-orcid":false,"given":"Jianzhi","family":"Shao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8302-1170","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0459-4723","authenticated-orcid":false,"given":"Chengfu","family":"Huo","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1367497.1367714"},{"key":"e_1_3_2_1_2_1","volume-title":"A review of ontology based query expansion. Information processing & management","author":"Bhogal Jagdev","year":"2007","unstructured":"Jagdev Bhogal, Andrew MacFarlane, and Peter Smith. 2007. A review of ontology based query expansion. Information processing & management, Vol. 43, 4 (2007), 866-886."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390377"},{"key":"e_1_3_2_1_4_1","volume-title":"Deep reinforcement learning from human preferences. Advances in neural information processing systems","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511489"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680109"},{"key":"e_1_3_2_1_7_1","volume-title":"Kto: Model alignment as prospect theoretic optimization. arXiv preprint arXiv:2402.01306","author":"Ethayarajh Kawin","year":"2024","unstructured":"Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky, and Douwe Kiela. 2024. Kto: Model alignment as prospect theoretic optimization. arXiv preprint arXiv:2402.01306 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Thinkless: Llm learns when to think. arXiv preprint arXiv:2505.13379","author":"Fang Gongfan","year":"2025","unstructured":"Gongfan Fang, Xinyin Ma, and Xinchao Wang. 2025. Thinkless: Llm learns when to think. arXiv preprint arXiv:2505.13379 (2025)."},{"key":"e_1_3_2_1_9_1","volume-title":"Efficient reasoning models: A survey. arXiv preprint arXiv:2504.10903","author":"Feng Sicheng","year":"2025","unstructured":"Sicheng Feng, Gongfan Fang, Xinyin Ma, and Xinchao Wang. 2025a. Efficient reasoning models: A survey. arXiv preprint arXiv:2504.10903 (2025)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737204"},{"key":"e_1_3_2_1_11_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_12_1","unstructured":"Aaron Jaech Adam Kalai Adam Lerer Adam Richardson Ahmed El-Kishky Aiden Low Alec Helyar Aleksander Madry Alex Beutel Alex Carney et al. 2024. Openai o1 system card. arXiv preprint arXiv:2412.16720 (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219850"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557068"},{"key":"e_1_3_2_1_15_1","volume-title":"AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning. arXiv preprint arXiv:2505.11896","author":"Lou Chenwei","year":"2025","unstructured":"Chenwei Lou, Zewei Sun, Xinnian Liang, Meng Qu, Wei Shen, Wenqi Wang, Yuntao Li, Qingping Yang, and Shuangzhi Wu. 2025. AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning. arXiv preprint arXiv:2505.11896 (2025)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591992"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358151"},{"key":"e_1_3_2_1_18_1","unstructured":"Aritra Mandal Ishita K Khan and Prathyusha Senthil Kumar. 2019. Query Rewriting using Automatic Synonym Extraction for E-commerce Search.. In eCOM@ SIGIR."},{"key":"e_1_3_2_1_19_1","volume-title":"Shimeng Yang, Pritom Saha Akash, and Kevin Chen-Chuan Chang.","author":"Nguyen Duy A","year":"2025","unstructured":"Duy A Nguyen, Rishi Kesav Mohan, Shimeng Yang, Pritom Saha Akash, and Kevin Chen-Chuan Chang. 2025. MiniELM: A Lightweight and Adaptive Query Rewriting Framework for E-Commerce Search Optimization. In Findings of the Association for Computational Linguistics: ACL 2025. 6952-6964."},{"key":"e_1_3_2_1_20_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_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3648298"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00276"},{"key":"e_1_3_2_1_23_1","volume-title":"Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 36 (2023), 53728-53741."},{"key":"e_1_3_2_1_24_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_25_1","volume-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, et al., 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29865"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441819"},{"key":"e_1_3_2_1_28_1","volume-title":"Learning to summarize with human feedback. Advances in neural information processing systems","author":"Stiennon Nisan","year":"2020","unstructured":"Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F Christiano. 2020. Learning to summarize with human feedback. Advances in neural information processing systems, Vol. 33 (2020), 3008-3021."},{"key":"e_1_3_2_1_29_1","unstructured":"Yang Sui Yu-Neng Chuang Guanchu Wang Jiamu Zhang Tianyi Zhang Jiayi Yuan Hongyi Liu Andrew Wen Shaochen Zhong Hanjie Chen et al. 2025. Stop overthinking: A survey on efficient reasoning for large language models. arXiv preprint arXiv:2503.16419 (2025)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148201"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3471158.3472250"},{"key":"e_1_3_2_1_32_1","volume-title":"Queen: Neural query rewriting in e-commerce.","author":"Wang Yaxuan","year":"2021","unstructured":"Yaxuan Wang, Hanqing Lu, Yunwen Xu, Rahul Goutam, Yiwei Song, and Bing Yin. 2021a. Queen: Neural query rewriting in e-commerce. (2021)."},{"key":"e_1_3_2_1_33_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_1_34_1","volume-title":"Lapo: Internalizing reasoning efficiency via length-adaptive policy optimization. arXiv preprint arXiv:2507.15758","author":"Wu Xingyu","year":"2025","unstructured":"Xingyu Wu, Yuchen Yan, Shangke Lyu, Linjuan Wu, Yiwen Qiu, Yongliang Shen, Weiming Lu, Jian Shao, Jun Xiao, and Yueting Zhuang. 2025. Lapo: Internalizing reasoning efficiency via length-adaptive policy optimization. arXiv preprint arXiv:2507.15758 (2025)."},{"key":"e_1_3_2_1_35_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_36_1","volume-title":"Rrhf: Rank responses to align language models with human feedback without tears. arXiv preprint arXiv:2304.05302","author":"Yuan Zheng","year":"2023","unstructured":"Zheng Yuan, Hongyi Yuan, Chuanqi Tan, Wei Wang, Songfang Huang, and Fei Huang. 2023. Rrhf: Rank responses to align language models with human feedback without tears. arXiv preprint arXiv:2304.05302 (2023)."},{"key":"e_1_3_2_1_37_1","volume-title":"Adaptthink: Reasoning models can learn when to think. arXiv preprint arXiv:2505.13417","author":"Zhang Jiajie","year":"2025","unstructured":"Jiajie Zhang, Nianyi Lin, Lei Hou, Ling Feng, and Juanzi Li. 2025. Adaptthink: Reasoning models can learn when to think. arXiv preprint arXiv:2505.13417 (2025)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3731950"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:35:40Z","timestamp":1775838940000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792806"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":38,"alternative-id":["10.1145\/3774904.3792806","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792806","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}