{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:49:51Z","timestamp":1777873791064,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737193","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:05:41Z","timestamp":1754255141000},"page":"5171-5181","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Applying Large Language Model For Relevance Search In Tencent"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9776-2404","authenticated-orcid":false,"given":"Dezhi","family":"Ye","sequence":"first","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3791-5005","authenticated-orcid":false,"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9037-8537","authenticated-orcid":false,"given":"Junwei","family":"Hu","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8816-3767","authenticated-orcid":false,"given":"Jiabin","family":"Fan","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8426-6448","authenticated-orcid":false,"given":"Bowen","family":"Tian","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3464-9192","authenticated-orcid":false,"given":"Haijin","family":"Liang","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5837-6144","authenticated-orcid":false,"given":"Jin","family":"Ma","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","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_2_2_1","volume-title":"Inpars: Data augmentation for information retrieval using large language models. arXiv preprint arXiv:2202.05144(2022).","author":"Bonifacio Luiz","year":"2022","unstructured":"Luiz Bonifacio, Hugo Abonizio, Marzieh Fadaee, and Rodrigo Nogueira. 2022. Inpars: Data augmentation for information retrieval using large language models. arXiv preprint arXiv:2202.05144(2022)."},{"key":"e_1_3_2_2_3_1","unstructured":"Tom B Brown. 2020. Language models are few-shot learners. arXiv preprint arXiv:2005.14165(2020)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Jianlv Chen Shitao Xiao Peitian Zhang Kun Luo Defu Lian and Zheng Liu. 2024b. Bge m3-embedding: Multi-lingual multi-functionality multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216(2024).","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"e_1_3_2_2_5_1","unstructured":"Zeyuan Chen Haiyan Wu Kaixin Wu Wei Chen Mingjie Zhong Jia Xu Zhongyi Liu and Wei Zhang. 2024a. Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting. arXiv preprint arXiv:2408.09439(2024)."},{"key":"e_1_3_2_2_6_1","volume-title":"Promptagator: Few-shot dense retrieval from 8 examples. arXiv preprint arXiv:2209.11755(2022).","author":"Dai Zhuyun","year":"2022","unstructured":"Zhuyun Dai, Vincent Y Zhao, Ji Ma, Yi Luan, Jianmo Ni, Jing Lu, Anton Bakalov, Kelvin Guu, Keith B Hall, and Ming-Wei Chang. 2022. Promptagator: Few-shot dense retrieval from 8 examples. arXiv preprint arXiv:2209.11755(2022)."},{"key":"e_1_3_2_2_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018).","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578337.3605136"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657743"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3409256.3409838"},{"key":"e_1_3_2_2_11_1","volume-title":"Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654(2020).","author":"He Pengcheng","year":"2020","unstructured":"Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2020. Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654(2020)."},{"key":"e_1_3_2_2_12_1","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_2_13_1","unstructured":"Vitor Jeronymo Luiz Bonifacio Hugo Abonizio Marzieh Fadaee Roberto Lotufo Jakub Zavrel and Rodrigo Nogueira. 2023. Inpars-v2: Large language models as efficient dataset generators for information retrieval. arXiv preprint arXiv:2301.01820(2023)."},{"key":"e_1_3_2_2_14_1","unstructured":"Chankyu Lee Rajarshi Roy Mengyao Xu Jonathan Raiman Mohammad Shoeybi Bryan Catanzaro and Wei Ping. 2024b. NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models. arXiv preprint arXiv:2405.17428(2024)."},{"key":"e_1_3_2_2_15_1","volume-title":"Gecko: Versatile text embeddings distilled from large language models. arXiv preprint arXiv:2403.20327(2024).","author":"Lee Jinhyuk","year":"2024","unstructured":"Jinhyuk Lee, Zhuyun Dai, Xiaoqi Ren, Blair Chen, Daniel Cer, Jeremy R Cole, Kai Hui, Michael Boratko, Rajvi Kapadia, Wen Ding, et al., 2024a. Gecko: Versatile text embeddings distilled from large language models. arXiv preprint arXiv:2403.20327(2024)."},{"key":"e_1_3_2_2_16_1","unstructured":"Chaofan Li MingHao Qin Shitao Xiao Jianlyu Chen Kun Luo Yingxia Shao Defu Lian and Zheng Liu. 2024b. Making text embedders few-shot learners. arXiv preprint arXiv:2409.15700(2024)."},{"key":"e_1_3_2_2_17_1","unstructured":"Dawei Li Bohan Jiang Liangjie Huang Alimohammad Beigi Chengshuai Zhao Zhen Tan Amrita Bhattacharjee Yuxuan Jiang Canyu Chen Tianhao Wu et al. 2024a. From generation to judgment: Opportunities and challenges of llm-as-a-judge. arXiv preprint arXiv:2411.16594(2024)."},{"key":"e_1_3_2_2_18_1","unstructured":"Zongxi Li Xianming Li Yuzhang Liu Haoran Xie Jing Li Fu-lee Wang Qing Li and Xiaoqin Zhong. 2023. Label supervised llama finetuning. arXiv preprint arXiv:2310.01208(2023)."},{"key":"e_1_3_2_2_19_1","unstructured":"Percy Liang Rishi Bommasani Tony Lee Dimitris Tsipras Dilara Soylu Michihiro Yasunaga Yian Zhang Deepak Narayanan Yuhuai Wu Ananya Kumar et al. 2022. Holistic evaluation of language models. arXiv preprint arXiv:2211.09110(2022)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Qi Liu Bo Wang Nan Wang and Jiaxin Mao. 2024. Leveraging passage embeddings for efficient listwise reranking with large language models. arXiv preprint arXiv:2406.14848(2024).","DOI":"10.1145\/3696410.3714554"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_2_22_1","unstructured":"Xueguang Ma Xinyu Zhang Ronak Pradeep and Jimmy Lin. 2023. Zero-shot listwise document reranking with a large language model. arXiv preprint arXiv:2305.02156(2023)."},{"key":"e_1_3_2_2_23_1","volume-title":"Sgpt: Gpt sentence embeddings for semantic search. arXiv preprint arXiv:2202.08904(2022).","author":"Muennighoff Niklas","year":"2022","unstructured":"Niklas Muennighoff. 2022. Sgpt: Gpt sentence embeddings for semantic search. arXiv preprint arXiv:2202.08904(2022)."},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the AAAI conference on artificial intelligence","volume":"29","author":"Naeini Mahdi Pakdaman","year":"2015","unstructured":"Mahdi Pakdaman Naeini, Gregory Cooper, and Milos Hauskrecht. 2015. Obtaining well calibrated probabilities using bayesian binning. In Proceedings of the AAAI conference on artificial intelligence, Vol. 29."},{"key":"e_1_3_2_2_25_1","volume-title":"Smoothquant: Accurate and efficient 4-bit post-training weightquantization for llm. arXiv preprint arXiv:2312.03788(2023).","author":"Pan Jiayi","year":"2023","unstructured":"Jiayi Pan, Chengcan Wang, Kaifu Zheng, Yangguang Li, Zhenyu Wang, and Bin Feng. 2023. Smoothquant: Accurate and efficient 4-bit post-training weightquantization for llm. arXiv preprint arXiv:2312.03788(2023)."},{"key":"e_1_3_2_2_26_1","volume-title":"Rankvicuna: Zero-shot listwise document reranking with open-source large language models. arXiv preprint arXiv:2309.15088(2023).","author":"Pradeep Ronak","year":"2023","unstructured":"Ronak Pradeep, Sahel Sharifymoghaddam, and Jimmy Lin. 2023a. Rankvicuna: Zero-shot listwise document reranking with open-source large language models. arXiv preprint arXiv:2309.15088(2023)."},{"key":"e_1_3_2_2_27_1","unstructured":"Ronak Pradeep Sahel Sharifymoghaddam and Jimmy Lin. 2023b. RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze! arXiv preprint arXiv:2312.02724(2023)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Zhen Qin Rolf Jagerman Kai Hui Honglei Zhuang Junru Wu Le Yan Jiaming Shen Tianqi Liu Jialu Liu Donald Metzler et al. 2023a. Large language models are effective text rankers with pairwise ranking prompting. arXiv preprint arXiv:2306.17563(2023).","DOI":"10.18653\/v1\/2024.findings-naacl.97"},{"key":"e_1_3_2_2_29_1","volume-title":"Honglei Zhuang, He Zhang, Aijun Bai, Kai Hui, Le Yan, and Xuanhui Wang.","author":"Qin Zhen","year":"2023","unstructured":"Zhen Qin, Rolf Jagerman, Rama Kumar Pasumarthi, Honglei Zhuang, He Zhang, Aijun Bai, Kai Hui, Le Yan, and Xuanhui Wang. 2023b. RD-Suite: a benchmark for ranking distillation. Advances in Neural Information Processing Systems, Vol. 36 (2023)."},{"key":"e_1_3_2_2_30_1","volume-title":"Guglielmo Faggioli, Bhaskar Mitra, Paul Thomas, and Emine Yilmaz.","author":"Rahmani Hossein A","year":"2025","unstructured":"Hossein A Rahmani, Clemencia Siro, Mohammad Aliannejadi, Nick Craswell, Charles LA Clarke, Guglielmo Faggioli, Bhaskar Mitra, Paul Thomas, and Emine Yilmaz. 2025. Judging the judges: A collection of llm-generated relevance judgements. arXiv preprint arXiv:2502.13908(2025)."},{"key":"e_1_3_2_2_31_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 2368-2376","author":"Reddi Sashank","year":"2021","unstructured":"Sashank Reddi, Rama Kumar Pasumarthi, Aditya Menon, Ankit Singh Rawat, Felix Yu, Seungyeon Kim, Andreas Veit, and Sanjiv Kumar. 2021. Rankdistil: Knowledge distillation for ranking. In International Conference on Artificial Intelligence and Statistics. PMLR, 2368-2376."},{"key":"e_1_3_2_2_32_1","unstructured":"Devendra Singh Sachan Mike Lewis Mandar Joshi Armen Aghajanyan Wen-tau Yih Joelle Pineau and Luke Zettlemoyer. 2022. Improving passage retrieval with zero-shot question generation. arXiv preprint arXiv:2204.07496(2022)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Weiwei Sun Lingyong Yan Xinyu Ma Shuaiqiang Wang Pengjie Ren Zhumin Chen Dawei Yin and Zhaochun Ren. 2023. Is ChatGPT good at search? investigating large language models as re-ranking agents. arXiv preprint arXiv:2304.09542(2023).","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"e_1_3_2_2_34_1","unstructured":"Manveer Singh Tamber Ronak Pradeep and Jimmy Lin. 2023. Scaling Down LiTting Up: Efficient Zero-Shot Listwise Reranking with Seq2seq Encoder-Decoder Models. arXiv preprint arXiv:2312.16098(2023)."},{"key":"e_1_3_2_2_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_2_36_1","unstructured":"Liang Wang Nan Yang Xiaolong Huang Linjun Yang Rangan Majumder and Furu Wei. 2023. Improving text embeddings with large language models. arXiv preprint arXiv:2401.00368(2023)."},{"key":"e_1_3_2_2_37_1","volume-title":"International Conference on Machine Learning. PMLR, 38087-38099","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, and Song Han. 2023. Smoothquant: Accurate and efficient post-training quantization for large language models. In International Conference on Machine Learning. PMLR, 38087-38099."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441667"},{"key":"e_1_3_2_2_39_1","unstructured":"Dezhi Ye Junwei Hu Jiabin Fan Bowen Tian Jie Liu Haijin Liang and Jin Ma. 2024a. Best Practices for Distilling Large Language Models into BERT for Web Search Ranking. arXiv preprint arXiv:2411.04539(2024)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671517"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939677"},{"key":"e_1_3_2_2_42_1","first-page":"609","article-title":"Obtaining calibrated probability estimates from decision trees and naive bayesian classifiers","volume":"1","author":"Zadrozny Bianca","year":"2001","unstructured":"Bianca Zadrozny and Charles Elkan. 2001. Obtaining calibrated probability estimates from decision trees and naive bayesian classifiers. In Icml, Vol. 1. 609-616.","journal-title":"Icml"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.706"},{"key":"e_1_3_2_2_44_1","first-page":"46595","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","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, et al., 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems, Vol. 36 (2023), 46595-46623.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3471158.3472238"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"crossref","unstructured":"Honglei Zhuang Zhen Qin Kai Hui Junru Wu Le Yan Xuanhui Wang and Michael Bendersky. 2023. Beyond yes and no: Improving zero-shot llm rankers via scoring fine-grained relevance labels. arXiv preprint arXiv:2310.14122(2023).","DOI":"10.18653\/v1\/2024.naacl-short.31"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"crossref","unstructured":"Shengyao Zhuang Xueguang Ma Bevan Koopman Jimmy Lin and Guido Zuccon. 2024a. PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval. arXiv preprint arXiv:2404.18424(2024).","DOI":"10.18653\/v1\/2024.emnlp-main.250"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657813"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467147"}],"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\/3711896.3737193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:21:01Z","timestamp":1777573261000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737193"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":49,"alternative-id":["10.1145\/3711896.3737193","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737193","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"}}]}}