{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T11:48:39Z","timestamp":1774352919576,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902209"],"award-info":[{"award-number":["61902209"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,28]]},"DOI":"10.1145\/3696410.3714554","type":"proceedings-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T23:08:29Z","timestamp":1745363309000},"page":"4274-4283","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4144-938X","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"first","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3698-9539","authenticated-orcid":false,"given":"Bo","family":"Wang","sequence":"additional","affiliation":[{"name":"Jina AI, Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8892-4287","authenticated-orcid":false,"given":"Nan","family":"Wang","sequence":"additional","affiliation":[{"name":"Jina AI, Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9257-5498","authenticated-orcid":false,"given":"Jiaxin","family":"Mao","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268","author":"Bajaj Payal","year":"2016","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":"TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy. arXiv preprint arXiv:2406.11678","author":"Chen Yiqun","year":"2024","unstructured":"Yiqun Chen, Qi Liu, Yi Zhang, Weiwei Sun, Daiting Shi, Jiaxin Mao, and Dawei Yin. 2024. TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy. arXiv preprint arXiv:2406.11678 (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token. arXiv preprint arXiv:2405.13792","author":"Cheng Xin","year":"2024","unstructured":"Xin Cheng, Xun Wang, Xingxing Zhang, Tao Ge, Si-Qing Chen, Furu Wei, Huishuai Zhang, and Dongyan Zhao. 2024. xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token. arXiv preprint arXiv:2405.13792 (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.232"},{"key":"e_1_3_2_1_5_1","volume-title":"Overview of the TREC 2019 deep learning track. arXiv preprint arXiv:2003","author":"Craswell Nick","year":"2020","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, and Ellen M Voorhees. 2020. Overview of the TREC 2019 deep learning track. arXiv preprint arXiv:2003.07820 (2020)."},{"key":"e_1_3_2_1_6_1","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems, Vol. 35 (2022), 16344--16359.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","volume-title":"In-context autoencoder for context compression in a large language model. arXiv preprint arXiv:2307.06945","author":"Ge Tao","year":"2023","unstructured":"Tao Ge, Jing Hu, Xun Wang, Si-Qing Chen, and Furu Wei. 2023. In-context autoencoder for context compression in a large language model. arXiv preprint arXiv:2307.06945 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"Susana Guzman, Georgios Mastrapas, Saba Sturua, Bo Wang, et al.","author":"G\u00fcnther Michael","year":"2023","unstructured":"Michael G\u00fcnther, Jackmin Ong, Isabelle Mohr, Alaeddine Abdessalem, Tanguy Abel, Mohammad Kalim Akram, Susana Guzman, Georgios Mastrapas, Saba Sturua, Bo Wang, et al. 2023. Jina embeddings 2: 8192-token general-purpose text embeddings for long documents. arXiv preprint arXiv:2310.19923 (2023)."},{"key":"e_1_3_2_1_9_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, Vol. 24, 251 (2023), 1--43.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_10_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023a. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_13_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_1_14_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024a. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language Models. arXiv preprint arXiv:2412.14574","author":"Liu Wenhan","year":"2024","unstructured":"Wenhan Liu, Xinyu Ma, Yutao Zhu, Ziliang Zhao, Shuaiqiang Wang, Dawei Yin, and Zhicheng Dou. 2024b. Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language Models. arXiv preprint arXiv:2412.14574 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Demorank: Selecting effective demonstrations for large language models in ranking task. arXiv preprint arXiv:2406.16332","author":"Liu Wenhan","year":"2024","unstructured":"Wenhan Liu, Yutao Zhu, and Zhicheng Dou. 2024c. Demorank: Selecting effective demonstrations for large language models in ranking task. arXiv preprint arXiv:2406.16332 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Zero-shot listwise document reranking with a large language model. arXiv preprint arXiv:2305.02156","author":"Ma Xueguang","year":"2023","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_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148246"},{"key":"e_1_3_2_1_19_1","volume-title":"Andreas Koukounas, Michael G\u00fcnther, Georgios Mastrapas, Vinit Ravishankar, Joan Fontanals Mart\u00ednez, Feng Wang, et al.","author":"Mohr Isabelle","year":"2024","unstructured":"Isabelle Mohr, Markus Krimmel, Saba Sturua, Mohammad Kalim Akram, Andreas Koukounas, Michael G\u00fcnther, Georgios Mastrapas, Vinit Ravishankar, Joan Fontanals Mart\u00ednez, Feng Wang, et al. 2024. Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings. arXiv preprint arXiv:2402.17016 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.765"},{"key":"e_1_3_2_1_21_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Mu Jesse","year":"2024","unstructured":"Jesse Mu, Xiang Li, and Noah Goodman. 2024. Learning to compress prompts with gist tokens. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"MTEB: Massive text embedding benchmark. arXiv preprint arXiv:2210.07316","author":"Muennighoff Niklas","year":"2022","unstructured":"Niklas Muennighoff, Nouamane Tazi, Lo\u00efc Magne, and Nils Reimers. 2022. MTEB: Massive text embedding benchmark. arXiv preprint arXiv:2210.07316 (2022)."},{"key":"e_1_3_2_1_23_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_24_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_25_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_27_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_28_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. 2023a. Rankvicuna: Zero-shot listwise document reranking with open-source large language models. arXiv preprint arXiv:2309.15088 (2023)."},{"key":"e_1_3_2_1_29_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. 2023b. RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze! arXiv preprint arXiv:2312.02724 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Zhen Qin Rolf Jagerman Kai Hui Honglei Zhuang Junru Wu Jiaming Shen Tianqi Liu Jialu Liu Donald Metzler Xuanhui Wang et al. 2023. 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_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_32_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_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"e_1_3_2_1_34_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_35_1","volume-title":"Efficient guided generation for llms. arXiv preprint arXiv:2307.09702","author":"Willard Brandon T","year":"2023","unstructured":"Brandon T Willard and R\u00e9mi Louf. 2023. Efficient guided generation for llms. arXiv preprint arXiv:2307.09702 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390306"},{"key":"e_1_3_2_1_37_1","volume-title":"C-pack: Packaged resources to advance general chinese embedding. arXiv preprint arXiv:2309.07597","author":"Xiao Shitao","year":"2023","unstructured":"Shitao Xiao, Zheng Liu, Peitian Zhang, and Niklas Muennighof. 2023. C-pack: Packaged resources to advance general chinese embedding. arXiv preprint arXiv:2309.07597 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Recomp: Improving retrieval-augmented lms with compression and selective augmentation. arXiv preprint arXiv:2310.04408","author":"Xu Fangyuan","year":"2023","unstructured":"Fangyuan Xu, Weijia Shi, and Eunsol Choi. 2023. Recomp: Improving retrieval-augmented lms with compression and selective augmentation. arXiv preprint arXiv:2310.04408 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval. arXiv preprint arXiv:2402.15838","author":"Yoon Soyoung","year":"2024","unstructured":"Soyoung Yoon, Eunbi Lee, Jiyeon Kim, Yireun Kim, Hyeongu Yun, and Seung-won Hwang. 2024. ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval. arXiv preprint arXiv:2402.15838 (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"Rank-without-gpt: Building gpt-independent listwise rerankers on open-source large language models. arXiv preprint arXiv:2312.02969","author":"Zhang Xinyu","year":"2023","unstructured":"Xinyu Zhang, Sebastian Hofst\u00e4tter, Patrick Lewis, Raphael Tang, and Jimmy Lin. 2023. Rank-without-gpt: Building gpt-independent listwise rerankers on open-source large language models. arXiv preprint arXiv:2312.02969 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"A setwise approach for effective and highly efficient zero-shot ranking with large language models. arXiv preprint arXiv:2310.09497","author":"Zhuang Shengyao","year":"2023","unstructured":"Shengyao Zhuang, Honglei Zhuang, Bevan Koopman, and Guido Zuccon. 2023. A setwise approach for effective and highly efficient zero-shot ranking with large language models. arXiv preprint arXiv:2310.09497 (2023)."}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714554","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:33Z","timestamp":1750295913000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714554"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":40,"alternative-id":["10.1145\/3696410.3714554","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714554","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}