{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:10Z","timestamp":1784179090015,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":60,"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":["Nos. U24A20253, 62272054, 62192784, 62276171"],"award-info":[{"award-number":["Nos. U24A20253, 62272054, 62192784, 62276171"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the National Key R&D Program of China","award":["No. 2023YFF0725103"],"award-info":[{"award-number":["No. 2023YFF0725103"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["No. 20230484319"],"award-info":[{"award-number":["No. 20230484319"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Xiaomi Young Talents Program"},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["Nos. 2024A1515011938"],"award-info":[{"award-number":["Nos. 2024A1515011938"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,28]]},"DOI":"10.1145\/3696410.3714620","type":"proceedings-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T16:42:02Z","timestamp":1746463322000},"page":"3942-3951","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Fitting Into Any Shape: A Flexible LLM-Based Re-Ranker With Configurable Depth and Width"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7765-8466","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6189-9456","authenticated-orcid":false,"given":"Chaofan","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2567-6843","authenticated-orcid":false,"given":"Shitao","family":"Xiao","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8179-7503","authenticated-orcid":false,"given":"Chaozhuo","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3306-9317","authenticated-orcid":false,"given":"Chen Jason","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1223-6996","authenticated-orcid":false,"given":"Hao","family":"Liao","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3507-9607","authenticated-orcid":false,"given":"Defu","family":"Lian","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8559-2628","authenticated-orcid":false,"given":"Yingxia","family":"Shao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Harkirat Behl, et al.","author":"Abdin Marah","year":"2024","unstructured":"Marah Abdin, Sam Ade Jacobs, Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Harkirat Behl, et al. 2024. Phi-3 technical report: A highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219 (2024)."},{"key":"e_1_3_2_1_2_1","volume-title":"Reading wikipedia to answer open-domain questions. arXiv preprint arXiv:1704.00051","author":"Chen Danqi","year":"2017","unstructured":"Danqi Chen, Adam Fisch, Jason Weston, and Antoine Bordes. 2017. Reading wikipedia to answer open-domain questions. arXiv preprint arXiv:1704.00051 (2017)."},{"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","volume-title":"Overview of the TREC 2020 deep learning track. CoRR","volume":"2102","author":"Craswell Nick","year":"2021","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, and Daniel Campos. 2021. Overview of the TREC 2020 deep learning track. CoRR, Vol. abs\/2102.07662 (2021). showeprint[arXiv]2102.07662 https:\/\/arxiv.org\/abs\/2102.07662"},{"key":"e_1_3_2_1_5_1","volume-title":"Overview of the TREC 2019 deep learning track. CoRR","volume":"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. CoRR, Vol. abs\/2003.07820 (2020). showeprint[arXiv]2003.07820 https:\/\/arxiv.org\/abs\/2003.07820"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401204"},{"key":"e_1_3_2_1_7_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Dettmers Tim","year":"2024","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2024. Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_9_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 preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_1_11_1","volume-title":"Precise zero-shot dense retrieval without relevance labels. arXiv preprint arXiv:2212.10496","author":"Gao Luyu","year":"2022","unstructured":"Luyu Gao, Xueguang Ma, Jimmy Lin, and Jamie Callan. 2022. Precise zero-shot dense retrieval without relevance labels. arXiv preprint arXiv:2212.10496 (2022)."},{"key":"e_1_3_2_1_12_1","unstructured":"Google DeepMind Gemma Team. 2024. Gemma 2: Improving Open Language Models at a Practical Size. https:\/\/storage.googleapis.com\/deepmind-media\/gemma\/gemma-2-report.pdf"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102067"},{"key":"e_1_3_2_1_14_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_15_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_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_1_17_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. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas O\u011fuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_20_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, Vol. 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_21_1","volume-title":"Making large language models a better foundation for dense retrieval. arXiv preprint arXiv:2312.15503","author":"Li Chaofan","year":"2023","unstructured":"Chaofan Li, Zheng Liu, Shitao Xiao, and Yingxia Shao. 2023a. Making large language models a better foundation for dense retrieval. arXiv preprint arXiv:2312.15503 (2023)."},{"key":"e_1_3_2_1_22_1","unstructured":"Chaofan Li MingHao Qin Shitao Xiao Jianlyu Chen Kun Luo Yingxia Shao Defu Lian and Zheng Liu. 2024. Making Text Embedders Few-Shot Learners. arxiv: 2409.15700 [cs.IR] https:\/\/arxiv.org\/abs\/2409.15700"},{"key":"e_1_3_2_1_23_1","unstructured":"Chaofan Li Yingxia Shao Yawen Li and Zheng Liu. 2025. SEA-SQL: Semantic-Enhanced Text-to-SQL with Adaptive Refinement. arxiv: 2408.04919 [cs.DB] https:\/\/arxiv.org\/abs\/2408.04919"},{"key":"e_1_3_2_1_24_1","volume-title":"Loftq: Lora-fine-tuning-aware quantization for large language models. arXiv preprint arXiv:2310.08659","author":"Li Yixiao","year":"2023","unstructured":"Yixiao Li, Yifan Yu, Chen Liang, Pengcheng He, Nikos Karampatziakis, Weizhu Chen, and Tuo Zhao. 2023b. Loftq: Lora-fine-tuning-aware quantization for large language models. arXiv preprint arXiv:2310.08659 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on machine learning. PMLR, 5958--5968","author":"Li Zhuohan","year":"2020","unstructured":"Zhuohan Li, Eric Wallace, Sheng Shen, Kevin Lin, Kurt Keutzer, Dan Klein, and Joey Gonzalez. 2020. Train big, then compress: Rethinking model size for efficient training and inference of transformers. In International Conference on machine learning. PMLR, 5958--5968."},{"key":"e_1_3_2_1_26_1","volume-title":"A few brief notes on deepimpact, coil, and a conceptual framework for information retrieval techniques. arXiv preprint arXiv:2106.14807","author":"Lin Jimmy","year":"2021","unstructured":"Jimmy Lin and Xueguang Ma. 2021. A few brief notes on deepimpact, coil, and a conceptual framework for information retrieval techniques. arXiv preprint arXiv:2106.14807 (2021)."},{"key":"e_1_3_2_1_27_1","unstructured":"AI @ Meta Llama Team. 2024. The Llama 3 Herd of Models. arxiv: 2407.21783 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00369"},{"key":"e_1_3_2_1_29_1","volume-title":"Llm-pruner: On the structural pruning of large language models. Advances in neural information processing systems","author":"Ma Xinyin","year":"2023","unstructured":"Xinyin Ma, Gongfan Fang, and Xinchao Wang. 2023a. Llm-pruner: On the structural pruning of large language models. Advances in neural information processing systems, Vol. 36 (2023), 21702--21720."},{"key":"e_1_3_2_1_30_1","volume-title":"Fine-tuning llama for multi-stage text retrieval. arXiv preprint arXiv:2310.08319","author":"Ma Xueguang","year":"2023","unstructured":"Xueguang Ma, Liang Wang, Nan Yang, Furu Wei, and Jimmy Lin. 2023b. Fine-tuning llama for multi-stage text retrieval. arXiv preprint arXiv:2310.08319 (2023)."},{"key":"e_1_3_2_1_31_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_32_1","volume-title":"Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, et al.","author":"Neelakantan Arvind","year":"2022","unstructured":"Arvind Neelakantan, Tao Xu, Raul Puri, Alec Radford, Jesse Michael Han, Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, et al. 2022. Text and code embeddings by contrastive pre-training. arXiv preprint arXiv:2201.10005 (2022)."},{"key":"e_1_3_2_1_33_1","unstructured":"Tri Nguyen Mir Rosenberg Xia Song Jianfeng Gao Saurabh Tiwary Rangan Majumder and Li Deng. 2016a. Ms marco: A human-generated machine reading comprehension dataset. (2016)."},{"key":"e_1_3_2_1_34_1","unstructured":"Tri Nguyen Mir Rosenberg Xia Song Jianfeng Gao Saurabh Tiwary Rangan Majumder and Li Deng. 2016b. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. In Proceedings of the Workshop on Cognitive Computation: Integrating neural and symbolic approaches 2016 co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016) Barcelona Spain December 9 2016 (CEUR Workshop Proceedings Vol. 1773) Tarek Richard Besold Antoine Bordes Artur S. d'Avila Garcez and Greg Wayne (Eds.). CEUR-WS.org. https:\/\/ceur-ws.org\/Vol-1773\/CoCoNIPS_2016_paper9.pdf"},{"key":"e_1_3_2_1_35_1","unstructured":"Jianmo Ni Chen Qu Jing Lu Zhuyun Dai Gustavo Hern\u00e1ndez \u00c1brego Ji Ma Vincent Y Zhao Yi Luan Keith B Hall Ming-Wei Chang et al. 2021. Large dual encoders are generalizable retrievers. arXiv preprint arXiv:2112.07899 (2021)."},{"key":"e_1_3_2_1_36_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_37_1","volume-title":"From doc2query to docTTTTTquery. Online preprint","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Jimmy Lin, and AI Epistemic. 2019a. From doc2query to docTTTTTquery. Online preprint, Vol. 6, 2 (2019)."},{"key":"e_1_3_2_1_38_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. 2019b. Multi-stage document ranking with BERT. arXiv preprint arXiv:1910.14424 (2019)."},{"key":"e_1_3_2_1_39_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_40_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_41_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, Vol. 21, 140 (2020), 1--67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_42_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_44_1","volume-title":"Is chatgpt good at search? investigating large language models as re-ranking agent. arXiv preprint arXiv:2304.09542","author":"Sun Weiwei","year":"2023","unstructured":"Weiwei Sun, Lingyong Yan, Xinyu Ma, Pengjie Ren, Dawei Yin, and Zhaochun Ren. 2023. Is chatgpt good at search? investigating large language models as re-ranking agent. arXiv preprint arXiv:2304.09542 (2023)."},{"key":"e_1_3_2_1_45_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_46_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023a. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_47_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023b. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of The Eighth Text REtrieval Conference, TREC 1999","author":"Voorhees Ellen M.","year":"1999","unstructured":"Ellen M. Voorhees. 1999. The TREC-8 Question Answering Track Report. In Proceedings of The Eighth Text REtrieval Conference, TREC 1999, Gaithersburg, Maryland, USA, November 17--19, 1999 (NIST Special Publication, Vol. 500--246), Ellen M. Voorhees and Donna K. Harman (Eds.). National Institute of Standards and Technology (NIST). http:\/\/trec.nist.gov\/pubs\/trec8\/papers\/qa_report.pdf"},{"key":"e_1_3_2_1_49_1","volume-title":"Simlm: Pre-training with representation bottleneck for dense passage retrieval. arXiv preprint arXiv:2207.02578","author":"Wang Liang","year":"2022","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022a. Simlm: Pre-training with representation bottleneck for dense passage retrieval. arXiv preprint arXiv:2207.02578 (2022)."},{"key":"e_1_3_2_1_50_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. 2022b. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)."},{"key":"e_1_3_2_1_51_1","unstructured":"Liang Wang Nan Yang Xiaolong Huang Linjun Yang Rangan Majumder and Furu Wei. 2024a. Improving Text Embeddings with Large Language Models. arxiv: 2401.00368 [cs.CL] https:\/\/arxiv.org\/abs\/2401.00368"},{"key":"e_1_3_2_1_52_1","volume-title":"Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672","author":"Wang Liang","year":"2024","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024b. Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672 (2024)."},{"key":"e_1_3_2_1_53_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_54_1","volume-title":"Sheared llama: Accelerating language model pre-training via structured pruning. arXiv preprint arXiv:2310.06694","author":"Xia Mengzhou","year":"2023","unstructured":"Mengzhou Xia, Tianyu Gao, Zhiyuan Zeng, and Danqi Chen. 2023. Sheared llama: Accelerating language model pre-training via structured pruning. arXiv preprint arXiv:2310.06694 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Shitao Xiao Zheng Liu Yingxia Shao and Zhao Cao. 2022. RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder. arxiv: 2205.12035 [cs.CL] https:\/\/arxiv.org\/abs\/2205.12035","DOI":"10.18653\/v1\/2022.emnlp-main.35"},{"key":"e_1_3_2_1_56_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_57_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang et al. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441667"},{"key":"e_1_3_2_1_59_1","volume-title":"INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning. arXiv preprint arXiv:2401.06532","author":"Zhu Yutao","year":"2024","unstructured":"Yutao Zhu, Peitian Zhang, Chenghao Zhang, Yifei Chen, Binyu Xie, Zhicheng Dou, Zheng Liu, and Ji-Rong Wen. 2024. INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning. arXiv preprint arXiv:2401.06532 (2024)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592047"}],"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\/3696410.3714620","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714620","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:56Z","timestamp":1750295936000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714620"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":60,"alternative-id":["10.1145\/3696410.3714620","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714620","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"}}]}}