{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:38:07Z","timestamp":1783737487383,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China &#x28;NSFC&#x29;","award":["62302486"],"award-info":[{"award-number":["62302486"]}]},{"name":"Innovation Funding of ICT CAS","award":["E361140"],"award-info":[{"award-number":["E361140"]}]},{"name":"CAS Special Research Assistant Funding Project","award":["JCKY2022130C039"],"award-info":[{"award-number":["JCKY2022130C039"]}]},{"name":"Strategic Priority Research Program of the CAS","award":["XDB0680102"],"award-info":[{"award-number":["XDB0680102"]}]},{"name":"NSFC","award":["62441229"],"award-info":[{"award-number":["62441229"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,7]]},"DOI":"10.1145\/3767695.3769496","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:14:58Z","timestamp":1764782098000},"page":"22-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1144-1298","authenticated-orcid":false,"given":"Hengran","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-4999","authenticated-orcid":false,"given":"Keping","family":"Bi","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, ICT, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9509-8674","authenticated-orcid":false,"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8687-4713","authenticated-orcid":false,"given":"Jiaming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Baidu Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9212-1947","authenticated-orcid":false,"given":"Shuaiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0684-6205","authenticated-orcid":false,"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[{"name":"Baidu Inc, Beijing, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5201-8195","authenticated-orcid":false,"given":"Xueqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_2_1_1_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_2_1","volume-title":"CLEF 2020, Thessaloniki, Greece, September 22--25, 2020, Proceedings 11","author":"Bondarenko Alexander","year":"2020","unstructured":"Alexander Bondarenko, Maik Fr\u00f6be, Meriem Beloucif, Lukas Gienapp, Yamen Ajjour, Alexander Panchenko, Chris Biemann, Benno Stein, Henning Wachsmuth, Martin Potthast, et al. 2020. Overview of Touch\u00e9 2020: argument retrieval. In Experimental IR Meets Multilinguality, Multimodality, and Interaction: 11th International Conference of the CLEF Association, CLEF 2020, Thessaloniki, Greece, September 22--25, 2020, Proceedings 11. Springer, 384--395."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30671-1_58"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102363"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.207"},{"key":"e_1_3_2_1_7_1","volume-title":"OVERVIEW OF THE TREC 2019 DEEP LEARNING TRACK. https:\/\/trec.nist.gov\/pubs\/trec28\/papers\/OVERVIEW.DL.pdf","author":"Nick","year":"2019","unstructured":"Nick Craswell1, Bhaskar Mitra1, Emine Yilmaz2, Daniel Campos1, and Ellen M. Voorhees3. 2019. OVERVIEW OF THE TREC 2019 DEEP LEARNING TRACK. https:\/\/trec.nist.gov\/pubs\/trec28\/papers\/OVERVIEW.DL.pdf (2019)."},{"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":"10.1007\/978-3-030-72240-1_26"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331403"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080751"},{"key":"e_1_3_2_1_12_1","first-page":"1","article-title":"Atlas: Few-shot learning with retrieval augmented language models","volume":"24","author":"Izacard Gautier","year":"2023","unstructured":"Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2023. Atlas: Few-shot learning with retrieval augmented language models. Journal of Machine Learning Research 24, 251 (2023), 1--43.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_13_1","volume-title":"Neftune: Noisy embeddings improve instruction finetuning. arXiv preprint arXiv:2310.05914","author":"Jain Neel","year":"2023","unstructured":"Neel Jain, Ping-yeh Chiang, Yuxin Wen, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian R Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, et al. 2023. Neftune: Noisy embeddings improve instruction finetuning. arXiv preprint arXiv:2310.05914 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Bridging the preference gap between retrievers and llms. arXiv preprint arXiv:2401.06954","author":"Ke Zixuan","year":"2024","unstructured":"Zixuan Ke, Weize Kong, Cheng Li, Mingyang Zhang, Qiaozhu Mei, and Michael Bendersky. 2024. Bridging the preference gap between retrievers and llms. arXiv preprint arXiv:2401.06954 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714554"},{"key":"e_1_3_2_1_18_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_19_1","volume-title":"Document ranking with a pretrained sequence-to-sequence model. arXiv preprint arXiv:2003.06713","author":"Nogueira Rodrigo","year":"2020","unstructured":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin. 2020. Document ranking with a pretrained sequence-to-sequence model. arXiv preprint arXiv:2003.06713 (2020)."},{"key":"e_1_3_2_1_20_1","volume-title":"Multi-stage document ranking with BERT. arXiv preprint arXiv:1910.14424","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Kyunghyun Cho, and Jimmy Lin. 2019. Multi-stage document ranking with BERT. arXiv preprint arXiv:1910.14424 (2019)."},{"key":"e_1_3_2_1_21_1","volume-title":"The expando-mono-duo design pattern for text ranking with pretrained sequence-to-sequence models. arXiv preprint arXiv:2101.05667","author":"Pradeep Ronak","year":"2021","unstructured":"Ronak Pradeep, Rodrigo Nogueira, and Jimmy Lin. 2021. The expando-mono-duo design pattern for text ranking with pretrained sequence-to-sequence models. arXiv preprint arXiv:2101.05667 (2021)."},{"key":"e_1_3_2_1_22_1","volume-title":"Rankvicuna: Zero-shot listwise document reranking with open-source large language models. arXiv preprint arXiv:2309.15088","author":"Pradeep Ronak","year":"2023","unstructured":"Ronak Pradeep, Sahel Sharifymoghaddam, and Jimmy Lin. 2023. Rankvicuna: Zero-shot listwise document reranking with open-source large language models. arXiv preprint arXiv:2309.15088 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze! arXiv preprint arXiv:2312.02724","author":"Pradeep Ronak","year":"2023","unstructured":"Ronak Pradeep, Sahel Sharifymoghaddam, and Jimmy Lin. 2023. RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze! arXiv preprint arXiv:2312.02724 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Deevya Swain, Avirup Sil, and Heng Ji.","author":"Reddy Revanth Gangi","year":"2024","unstructured":"Revanth Gangi Reddy, JaeHyeok Doo, Yifei Xu, Md Arafat Sultan, Deevya Swain, Avirup Sil, and Heng Ji. 2024. FIRST: Faster Improved Listwise Reranking with Single Token Decoding. arXiv preprint arXiv:2406.15657 (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714658"},{"key":"e_1_3_2_1_26_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_27_1","volume-title":"Improving passage retrieval with zero-shot question generation. arXiv preprint arXiv:2204.07496","author":"Sachan Devendra Singh","year":"2022","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_1_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(198805)39:3<161::AID-ASI2>3.0.CO;2-0"},{"key":"e_1_3_2_1_29_1","volume-title":"Relevance: The Search for a Definition.","author":"Schamber Linda","year":"1988","unstructured":"Linda Schamber and Michael Eisenberg. 1988. Relevance: The Search for a Definition. (1988)."},{"key":"e_1_3_2_1_30_1","volume-title":"Replug: Retrieval-augmented black-box language models. arXiv preprint arXiv:2301.12652","author":"Shi Weijia","year":"2023","unstructured":"Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Rich James, Mike Lewis, Luke Zettlemoyer, and Wen-tau Yih. 2023. Replug: Retrieval-augmented black-box language models. arXiv preprint arXiv:2301.12652 (2023)."},{"key":"e_1_3_2_1_31_1","first-page":"18","volume-title":"TREC 2019 News Track Overview. In TREC. 4","author":"Soboroff Ian","year":"2019","unstructured":"Ian Soboroff, Shudong Huang, and Donna Harman. 2019. TREC 2019 News Track Overview. In TREC. 4, 18 (2019)."},{"key":"e_1_3_2_1_32_1","volume-title":"Is ChatGPT good at search? investigating large language models as re-ranking agents. arXiv preprint arXiv:2304.09542","author":"Sun Weiwei","year":"2023","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)."},{"key":"e_1_3_2_1_33_1","unstructured":"Qwen Team. 2024. Qwen2.5: A Party of Foundation Models. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"e_1_3_2_1_34_1","unstructured":"Qwen Team. 2025. Qwen3 Technical Report. arXiv:2505.09388 [cs.CL] https:\/\/arxiv.org\/abs\/2505.09388"},{"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","volume-title":"Overview of the TREC 2004 Robust Retrieval Track.","author":"Voorhees Ellen","year":"2005","unstructured":"Ellen Voorhees. 2005. Overview of the TREC 2004 Robust Retrieval Track. (2005)."},{"key":"e_1_3_2_1_37_1","volume-title":"ACM SIGIR Forum","volume":"54","author":"Voorhees Ellen","year":"2021","unstructured":"Ellen Voorhees, Tasmeer Alam, Steven Bedrick, Dina Demner-Fushman, William R Hersh, Kyle Lo, Kirk Roberts, Ian Soboroff, and Lucy Lu Wang. 2021. TREC-COVID: constructing a pandemic information retrieval test collection. In ACM SIGIR Forum, Vol. 54. ACM New York, NY, USA, 1--12."},{"key":"e_1_3_2_1_38_1","volume-title":"Madeleine van Zuylen, Arman Cohan, and Hannaneh Hajishirzi.","author":"Wadden David","year":"2020","unstructured":"David Wadden, Shanchuan Lin, Kyle Lo, Lucy Lu Wang, Madeleine van Zuylen, Arman Cohan, and Hannaneh Hajishirzi. 2020. Fact or fiction: Verifying scientific claims. arXiv preprint arXiv:2004.14974 (2020)."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 27th ACM international conference on information and knowledge management. 1313--1322","author":"Li Cheng","year":"2018","unstructured":"XuanhuiWang, Cheng Li, Nadav Golbandi, Michael Bendersky, and Marc Najork. 2018. The lambdaloss framework for ranking metric optimization. In Proceedings of the 27th ACM international conference on information and knowledge management. 1313--1322."},{"key":"e_1_3_2_1_40_1","unstructured":"Shitao Xiao Zheng Liu Peitian Zhang and Niklas Muennighoff. 2023. C-Pack: Packaged Resources To Advance General Chinese Embedding. arXiv:2309.07597 [cs.CL]"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"e_1_3_2_1_42_1","volume-title":"Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy. arXiv preprint arXiv:2406.11290","author":"Zhang Hengran","year":"2024","unstructured":"Hengran Zhang, Keping Bi, Jiafeng Guo, and Xueqi Cheng. 2024. Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy. arXiv preprint arXiv:2406.11290 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Leveraging LLMs for Utility-Focused Annotation: Reducing Manual Effort for Retrieval and RAG. arXiv preprint arXiv:2504.05220","author":"Zhang Hengran","year":"2025","unstructured":"Hengran Zhang, Minghao Tang, Keping Bi, Jiafeng Guo, Shihao Liu, Daiting Shi, Dawei Yin, and Xueqi Cheng. 2025. Leveraging LLMs for Utility-Focused Annotation: Reducing Manual Effort for Retrieval and RAG. arXiv preprint arXiv:2504.05220 (2025)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657784"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592047"}],"event":{"name":"SIGIR-AP 2025:Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","location":"Xi'an China","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region"],"original-title":[],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:15:47Z","timestamp":1764782147000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767695.3769496"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":45,"alternative-id":["10.1145\/3767695.3769496","10.1145\/3767695"],"URL":"https:\/\/doi.org\/10.1145\/3767695.3769496","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}