{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T18:25:28Z","timestamp":1775931928956,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","funder":[{"name":"Meituan Research Fund","award":["PO250624101698"],"award-info":[{"award-number":["PO250624101698"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792801","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"8222-8231","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0900-5900","authenticated-orcid":false,"given":"Runze","family":"Xia","sequence":"first","affiliation":[{"name":"Meituan, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2311-0344","authenticated-orcid":false,"given":"Yupeng","family":"Ji","sequence":"additional","affiliation":[{"name":"Meituan, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3639-5408","authenticated-orcid":false,"given":"Yuxi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Meituan, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7291-8205","authenticated-orcid":false,"given":"Haodong","family":"Liu","sequence":"additional","affiliation":[{"name":"Meituan, shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4199-2935","authenticated-orcid":false,"given":"Teng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meituan, shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1474-3692","authenticated-orcid":false,"given":"Piji","family":"Li","sequence":"additional","affiliation":[{"name":"Researcher, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics: Industry Track. 136-148","author":"Agrawal Sanjay","year":"2025","unstructured":"Sanjay Agrawal, Faizan Ahemad, and Vivek Varadarajan Sembium. 2025. Rationale-guided distillation for e-commerce relevance classification: Bridging large language models and lightweight cross-encoders. In Proceedings of the 31st International Conference on Computational Linguistics: Industry Track. 136-148."},{"key":"e_1_3_2_1_3_1","volume-title":"Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216","author":"Chen Jianlv","year":"2024","unstructured":"Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216 (2024)."},{"key":"e_1_3_2_1_4_1","first-page":"4171","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). 4171-4186."},{"key":"e_1_3_2_1_5_1","volume-title":"Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821","author":"Gao Tianyu","year":"2021","unstructured":"Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821 (2021)."},{"key":"e_1_3_2_1_6_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_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3486250"},{"key":"e_1_3_2_1_8_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_9_1","volume-title":"Improving efficient neural ranking models with cross-architecture knowledge distillation. arXiv preprint arXiv:2010.02666","author":"Hofst\u00e4tter Sebastian","year":"2020","unstructured":"Sebastian Hofst\u00e4tter, Sophia Althammer, Michael Schr\u00f6der, Mete Sertkan, and Allan Hanbury. 2020. Improving efficient neural ranking models with cross-architecture knowledge distillation. arXiv preprint arXiv:2010.02666 (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_1_11_1","volume-title":"Tinybert: Distilling bert for natural language understanding. arXiv preprint arXiv:1909.10351","author":"Jiao Xiaoqi","year":"2019","unstructured":"Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, and Qun Liu. 2019. Tinybert: Distilling bert for natural language understanding. arXiv preprint arXiv:1909.10351 (2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_14_1","volume-title":"Knowledge distillation based contextual relevance matching for e-commerce product search. arXiv preprint arXiv:2210.01701","author":"Liu Ziyang","year":"2022","unstructured":"Ziyang Liu, Chaokun Wang, Hao Feng, Lingfei Wu, and Liqun Yang. 2022. Knowledge distillation based contextual relevance matching for e-commerce product search. arXiv preprint arXiv:2210.01701 (2022)."},{"key":"e_1_3_2_1_15_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_16_1","volume-title":"Exploring Query Understanding for Amazon Product Search. In 2024 IEEE International Conference on Big Data (BigData). IEEE, 2343-2348","author":"Luo Chen","year":"2024","unstructured":"Chen Luo, Xianfeng Tang, Hanqing Lu, Yaochen Xie, Hui Liu, Zhenwei Dai, Limeng Cui, Ashutosh Joshi, Sreyashi Nag, Yang Li, et al., 2024. Exploring Query Understanding for Amazon Product Search. In 2024 IEEE International Conference on Big Data (BigData). IEEE, 2343-2348."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539164"},{"key":"e_1_3_2_1_18_1","unstructured":"Michinari Momma Chaosheng Dong and Yetian Chen. 2022. Multi-objective ranking with directions of preferences. (2022)."},{"key":"e_1_3_2_1_19_1","first-page":"278","volume-title":"Icml","volume":"99","author":"Ng Andrew Y","year":"1999","unstructured":"Andrew Y Ng, Daishi Harada, and Stuart Russell. 1999. Policy invariance under reward transformations: Theory and application to reward shaping. In Icml, Vol. 99. Citeseer, 278-287."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330759"},{"key":"e_1_3_2_1_21_1","volume-title":"Passage Re-ranking with BERT. arXiv preprint arXiv:1901.04085","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. arXiv preprint arXiv:1901.04085 (2019)."},{"key":"e_1_3_2_1_22_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_23_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al., 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3648298"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599816"},{"key":"e_1_3_2_1_26_1","first-page":"463","volume-title":"ICML","volume":"98","author":"Randl\u00f8v Jette","year":"1998","unstructured":"Jette Randl\u00f8v and Preben Alstr\u00f8m. 1998. Learning to Drive a Bicycle Using Reinforcement Learning and Shaping.. In ICML, Vol. 98. 463-471."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_28_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_29_1","first-page":"449","volume-title":"Knowledge Distillation for Enhancing Walmart E-commerce Search Relevance Using Large Language Models. In Companion Proceedings of the ACM on Web Conference","author":"Shang Hongwei","year":"2025","unstructured":"Hongwei Shang, Nguyen Vo, Nitin Yadav, Tian Zhang, Ajit Puthenputhussery, Xunfan Cai, Shuyi Chen, Prijith Chandran, and Changsung Kang. 2025. Knowledge Distillation for Enhancing Walmart E-commerce Search Relevance Using Large Language Models. In Companion Proceedings of the ACM on Web Conference 2025. 449-457."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696075"},{"key":"e_1_3_2_1_31_1","volume-title":"Mobilebert: a compact task-agnostic bert for resource-limited devices. arXiv preprint arXiv:2004.02984","author":"Sun Zhiqing","year":"2020","unstructured":"Zhiqing Sun, Hongkun Yu, Xiaodan Song, Renjie Liu, Yiming Yang, and Denny Zhou. 2020. Mobilebert: a compact task-agnostic bert for resource-limited devices. arXiv preprint arXiv:2004.02984 (2020)."},{"key":"e_1_3_2_1_32_1","volume-title":"Reward Hacking Mitigation using Verifiable Composite Rewards. arXiv preprint arXiv:2509.15557","author":"Bin Tarek Mirza Farhan","year":"2025","unstructured":"Mirza Farhan Bin Tarek and Rahmatollah Beheshti. 2025. Reward Hacking Mitigation using Verifiable Composite Rewards. arXiv preprint arXiv:2509.15557 (2025)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3627418"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3584638"},{"key":"e_1_3_2_1_35_1","volume-title":"Onur Gungor, Yu Xu, Krishna Kamath, Rakesh Chalasani, Kurchi Subhra Hazra, and Jinfeng Rao.","author":"Wang Han","year":"2024","unstructured":"Han Wang, Mukuntha Narayanan Sundararaman, Onur Gungor, Yu Xu, Krishna Kamath, Rakesh Chalasani, Kurchi Subhra Hazra, and Jinfeng Rao. 2024. Improving Pinterest Search Relevance Using Large Language Models. arXiv preprint arXiv:2410.17152 (2024)."},{"key":"e_1_3_2_1_36_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_37_1","volume-title":"DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation","author":"Xu Chen","year":"2025","unstructured":"Chen Xu, Tian Lan, Yu Ji, Changlong Yu, Wei Wang, Jun Gao, Qunxi Dong, Kun Qian, Piji Li, Wei Bi, et al., 2025. DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation. IEEE Transactions on Knowledge and Data Engineering (2025)."},{"key":"e_1_3_2_1_38_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025a. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_39_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. 2025b. Qwen3 Technical Report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539090"},{"key":"e_1_3_2_1_41_1","volume-title":"Best Practices for Distilling Large Language Models into BERT for Web Search Ranking. arXiv preprint arXiv:2411.04539","author":"Ye Dezhi","year":"2024","unstructured":"Dezhi Ye, Junwei Hu, Jiabin Fan, Bowen Tian, Jie Liu, Haijin Liang, and Jin Ma. 2024. Best Practices for Distilling Large Language Models into BERT for Web Search Ranking. arXiv preprint arXiv:2411.04539 (2024)."},{"key":"e_1_3_2_1_42_1","unstructured":"Chong Zhang Yue Deng Xiang Lin Bin Wang Dianwen Ng Hai Ye Xingxuan Li Yao Xiao Zhanfeng Mo Qi Zhang et al. 2025. 100 days after deepseek-r1: A survey on replication studies and more directions for reasoning language models. arXiv preprint arXiv:2505.00551 (2025)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"e_1_3_2_1_44_1","volume-title":"Distilling inter-class distance for semantic segmentation. arXiv preprint arXiv:2205.03650","author":"Zhang Zhengbo","year":"2022","unstructured":"Zhengbo Zhang, Chunluan Zhou, and Zhigang Tu. 2022. Distilling inter-class distance for semantic segmentation. arXiv preprint arXiv:2205.03650 (2022)."},{"key":"e_1_3_2_1_45_1","first-page":"631","volume-title":"Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning. In Companion Proceedings of the ACM on Web Conference","author":"Zhao Gang","year":"2025","unstructured":"Gang Zhao, Ximing Zhang, Chenji Lu, Hui Zhao, Tianshu Wu, Pengjie Wang, Jian Xu, and Bo Zheng. 2025. Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning. In Companion Proceedings of the ACM on Web Conference 2025. 631-640."},{"key":"e_1_3_2_1_46_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 Vol. 1 2 (2023)."}],"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":"2026-04-10T16:35:50Z","timestamp":1775838950000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792801"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":46,"alternative-id":["10.1145\/3774904.3792801","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792801","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"}}]}}