{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:03:47Z","timestamp":1780675427192,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792078","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:34Z","timestamp":1775771674000},"page":"1876-1886","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Generalized Pseudo-Relevance Feedback"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7392-0524","authenticated-orcid":false,"given":"Yiteng","family":"Tu","sequence":"first","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China and Quan Cheng Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8718-9402","authenticated-orcid":false,"given":"Weihang","family":"Su","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3530-3787","authenticated-orcid":false,"given":"Yujia","family":"Zhou","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0140-4512","authenticated-orcid":false,"given":"Yiqun","family":"Liu","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8728-3475","authenticated-orcid":false,"given":"Fen","family":"Lin","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7096-8527","authenticated-orcid":false,"given":"Qin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5030-709X","authenticated-orcid":false,"given":"Qingyao","family":"Ai","sequence":"additional","affiliation":[{"name":"Quan Cheng Laboratory, Beijing, China and DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Nasreen Abdul-Jaleel James Allan W Bruce Croft Fernando Diaz Leah Larkey Xiaoyan Li Mark D Smucker and Courtney Wade. 2004. UMass at TREC 2004: Novelty and HARD. (2004).","DOI":"10.21236\/ADA460118"},{"key":"e_1_3_2_1_2_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_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080813"},{"key":"e_1_3_2_1_4_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_5_1","unstructured":"Payal Bajaj Daniel Campos Nick Craswell Li Deng Jianfeng Gao Xiaodong Liu Rangan Majumder Andrew McNamara Bhaskar Mitra Tri Nguyen et al. 2016. Ms marco: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 (2016)."},{"key":"e_1_3_2_1_6_1","volume-title":"Overview of the TREC 2022 deep learning track. arXiv preprint arXiv:2507","author":"Craswell Nick","year":"2025","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, Jimmy Lin, Ellen M Voorhees, and Ian Soboroff. 2025. Overview of the TREC 2022 deep learning track. arXiv preprint arXiv:2507.10865 (2025)."},{"key":"e_1_3_2_1_7_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). 4171--4186."},{"key":"e_1_3_2_1_8_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 e-prints (2024) arXiv--2407."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657743"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.99"},{"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","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983769"},{"key":"e_1_3_2_1_13_1","volume-title":"Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118 (2021)."},{"key":"e_1_3_2_1_14_1","volume-title":"Query expansion by prompting large language models. arXiv preprint arXiv:2305.03653","author":"Jagerman Rolf","year":"2023","unstructured":"Rolf Jagerman, Honglei Zhuang, Zhen Qin, Xuanhui Wang, and Michael Bendersky. 2023. Query expansion by prompting large language models. arXiv preprint arXiv:2305.03653 (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_1_16_1","volume-title":"Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering.. In EMNLP (1). 6769--6781."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130348.3130376"},{"key":"e_1_3_2_1_19_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3570724"},{"key":"e_1_3_2_1_21_1","volume-title":"LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback. arXiv preprint arXiv:2504.01448","author":"Li Hang","year":"2025","unstructured":"Hang Li, Shengyao Zhuang, Bevan Koopman, and Guido Zuccon. 2025. LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback. arXiv preprint arXiv:2504.01448 (2025)."},{"key":"e_1_3_2_1_22_1","volume-title":"Query Expansion in the Age of Pretrained and Large Language Models: A Comprehensive Survey. arXiv preprint arXiv:2509.07794","author":"Li Minghan","year":"2025","unstructured":"Minghan Li, Xinxuan Lv, Junjie Zou, Tongna Chen, Chao Zhang, Suchao An, Ercong Nie, and Guodong Zhou. 2025. Query Expansion in the Age of Pretrained and Large Language Models: A Comprehensive Survey. arXiv preprint arXiv:2509.07794 (2025)."},{"key":"e_1_3_2_1_23_1","volume-title":"Roberta: A robustly optimized bert pre-training 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 pre-training approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591992"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Stephen Robertson Hugo Zaragoza et al. 2009. The probabilistic relevance framework: BM25 and beyond. Foundations and Trends\u00ae in Information Retrieval 3 4 (2009) 333--389.","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_26_1","volume-title":"Relevance feedback in information retrieval. The SMART retrieval system: experiments in automatic document processing","author":"Rocchio Joseph John","year":"1971","unstructured":"Joseph John Rocchio Jr. 1971. Relevance feedback in information retrieval. The SMART retrieval system: experiments in automatic document processing (1971)."},{"key":"e_1_3_2_1_27_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_28_1","volume-title":"Large language models are strong zero-shot retriever. arXiv preprint arXiv:2304.14233","author":"Shen Tao","year":"2023","unstructured":"Tao Shen, Guodong Long, Xiubo Geng, Chongyang Tao, Tianyi Zhou, and Daxin Jiang. 2023. Large language models are strong zero-shot retriever. arXiv preprint arXiv:2304.14233 (2023)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29869"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. 4118--4121","author":"Su Weihang","year":"2025","unstructured":"Weihang Su, Qingyao Ai, Jingtao Zhan, Qian Dong, and Yiqun Liu. 2025. Dynamic and parametric retrieval-augmented generation. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. 4118--4121."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3673791.3698403"},{"key":"e_1_3_2_1_32_1","volume-title":"DRAGIN: dynamic retrieval augmented generation based on the information needs of large language models. arXiv preprint arXiv:2403.10081","author":"Su Weihang","year":"2024","unstructured":"Weihang Su, Yichen Tang, Qingyao Ai, Zhijing Wu, and Yiqun Liu. 2024. DRAGIN: dynamic retrieval augmented generation based on the information needs of large language models. arXiv preprint arXiv:2403.10081 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729957"},{"key":"e_1_3_2_1_34_1","volume-title":"Unsupervised real-time hallucination detection based on the internal states of large language models. arXiv preprint arXiv:2403.06448","author":"Su Weihang","year":"2024","unstructured":"Weihang Su, Changyue Wang, Qingyao Ai, Yiran Hu, Zhijing Wu, Yujia Zhou, and Yiqun Liu. 2024. Unsupervised real-time hallucination detection based on the internal states of large language models. arXiv preprint arXiv:2403.06448 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663 (2021)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730078"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_7"},{"key":"e_1_3_2_1_38_1","volume-title":"Astute rag: Overcoming imperfect retrieval augmentation and knowledge conflicts for large language models. arXiv preprint arXiv:2410.07176","author":"Wang Fei","year":"2024","unstructured":"Fei Wang, Xingchen Wan, Ruoxi Sun, Jiefeng Chen, and Sercan \u00d6 Arik. 2024. Astute rag: Overcoming imperfect retrieval augmentation and knowledge conflicts for large language models. arXiv preprint arXiv:2410.07176 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533","author":"Wang Liang","year":"2022","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)."},{"key":"e_1_3_2_1_40_1","volume-title":"Query2doc: Query expansion with large language models. arXiv preprint arXiv:2303.07678","author":"Wang Liang","year":"2023","unstructured":"Liang Wang, Nan Yang, and Furu Wei. 2023. Query2doc: Query expansion with large language models. arXiv preprint arXiv:2303.07678 (2023)."},{"key":"e_1_3_2_1_41_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 35 (2022), 24824--24837."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"},{"key":"e_1_3_2_1_43_1","volume-title":"Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808","author":"Xiong Lee","year":"2020","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_1_44_1","volume-title":"Repbert: Contextualized text embeddings for first-stage retrieval. arXiv preprint arXiv:2006.15498","author":"Zhan Jingtao","year":"2020","unstructured":"Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Min Zhang, and Shaoping Ma. 2020. Repbert: Contextualized text embeddings for first-stage retrieval. arXiv preprint arXiv:2006.15498 (2020)."},{"key":"e_1_3_2_1_45_1","volume-title":"Knowledge-grounded dialogue generation with pre-trained language models. arXiv preprint arXiv:2010.08824","author":"Zhao Xueliang","year":"2020","unstructured":"Xueliang Zhao, Wei Wu, Can Xu, Chongyang Tao, Dongyan Zhao, and Rui Yan. 2020. Knowledge-grounded dialogue generation with pre-trained language models. arXiv preprint arXiv:2010.08824 (2020)."},{"key":"e_1_3_2_1_46_1","volume-title":"Large language models for information retrieval: A survey. arXiv preprint arXiv:2308.07107","author":"Zhu Yutao","year":"2023","unstructured":"Yutao Zhu, Huaying Yuan, Shuting Wang, Jiongnan Liu, Wenhan Liu, Chenlong Deng, Haonan Chen, Zheng Liu, Zhicheng Dou, and Ji-Rong Wen. 2023. Large language models for information retrieval: A survey. arXiv preprint arXiv:2308.07107 (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":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:33:36Z","timestamp":1780673616000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792078"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":46,"alternative-id":["10.1145\/3774904.3792078","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792078","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"}}]}}