{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:02:24Z","timestamp":1775815344799,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657951","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2421-2425","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":75,"title":["Fine-Tuning LLaMA for Multi-Stage Text Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3430-4910","authenticated-orcid":false,"given":"Xueguang","family":"Ma","sequence":"first","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4664-7136","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7379-2609","authenticated-orcid":false,"given":"Nan","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7810-5852","authenticated-orcid":false,"given":"Furu","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0661-7189","authenticated-orcid":false,"given":"Jimmy","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. 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, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv:1611.09268 (2016)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1171"},{"key":"e_1_3_2_1_3_1","volume-title":"Overview of the TREC 2020 Deep Learning Track. arXiv: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. arXiv:2102.07662 (2021)."},{"key":"e_1_3_2_1_4_1","volume-title":"Overview of the TREC 2019 Deep Learning Track. 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:2003.07820 (2020)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331303"},{"key":"e_1_3_2_1_6_1","volume-title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. arXiv:2307.08691","author":"Dao Tri","year":"2023","unstructured":"Tri Dao. 2023. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. arXiv:2307.08691 (2023)."},{"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","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531860"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.203"},{"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","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J.","year":"2022","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_12_1","volume-title":"Active Retrieval Augmented Generation. arXiv:2305.06983","author":"Jiang Zhengbao","year":"2023","unstructured":"Zhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. Active Retrieval Augmented Generation. arXiv:2305.06983 (2023)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_14_1","unstructured":"Aditya Kusupati Gantavya Bhatt Aniket Rege Matthew Wallingford Aditya Sinha Vivek Ramanujan William Howard-Snyder Kaifeng Chen Sham Kakade Prateek Jain and Ali Farhadi. 2022. Matryoshka Representation Learning. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_15_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\"aschel Sebastian Riedel and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems. 9459--9474."},{"key":"e_1_3_2_1_16_1","volume-title":"A Proposed Conceptual Framework for a Representational Approach to Information Retrieval. arXiv:2110.01529","author":"Lin Jimmy","year":"2021","unstructured":"Jimmy Lin. 2021. A Proposed Conceptual Framework for a Representational Approach to Information Retrieval. arXiv:2110.01529 (2021)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_1_18_1","volume-title":"Ronak Pradeep, and Jimmy Lin.","author":"Ma Xueguang","year":"2023","unstructured":"Xueguang Ma, Xinyu Crystina Zhang, Ronak Pradeep, and Jimmy Lin. 2023. Zero-Shot Listwise Document Reranking with a Large Language Model. arXiv:2305.02156 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"SGPT: GPT Sentence Embeddings for Semantic Search. arXiv:2202.08904","author":"Muennighoff Niklas","year":"2022","unstructured":"Niklas Muennighoff. 2022. SGPT: GPT Sentence Embeddings for Semantic Search. arXiv:2202.08904 (2022)."},{"key":"e_1_3_2_1_20_1","unstructured":"Arvind Neelakantan et al. 2022. Text and Code Embeddings by Contrastive Pre-Training. arXiv:2201.10005 (2022)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.669"},{"key":"e_1_3_2_1_22_1","volume-title":"Passage Re-ranking with BERT. arXiv:1901.04085","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. arXiv:1901.04085 (2019)."},{"key":"e_1_3_2_1_23_1","volume-title":"Multi-Stage Document Ranking with BERT. 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:1910.14424 (2019)."},{"key":"e_1_3_2_1_24_1","unstructured":"Open\u00adAI. 2023. GPT-4 Technical Report. arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.200"},{"key":"e_1_3_2_1_26_1","volume-title":"The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models. 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:2101.05667 (2021)."},{"key":"e_1_3_2_1_27_1","volume-title":"RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models. 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:2309.15088 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting. arXiv:2306.17563","author":"Qin Zhen","year":"2023","unstructured":"Zhen Qin, Rolf Jagerman, Kai Hui, Honglei Zhuang, Junru Wu, Jiaming Shen, Tianqi Liu, Jialu Liu, Donald Metzler, Xuanhui Wang, and Michael Bendersky. 2023. Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting. arXiv:2306.17563 (2023)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_1_30_1","first-page":"140","article-title":"2020. 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_31_1","volume-title":"REPLUG: Retrieval-Augmented Black-Box Language Models. 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:2301.12652 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent. 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:2304.09542 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1074"},{"key":"e_1_3_2_1_35_1","volume-title":"2023 a. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv:2307.09288","author":"Hugo Touvron","year":"2023","unstructured":"Hugo Touvron et al. 2023 a. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"2023 b. LLaMA: Open and Efficient Foundation Language Models. arXiv:2302.13971","author":"Hugo Touvron","year":"2023","unstructured":"Hugo Touvron et al. 2023 b. LLaMA: Open and Efficient Foundation Language Models. arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_37_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.125"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.585"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.35"},{"key":"e_1_3_2_1_41_1","volume-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In International Conference on Learning Representations.","author":"Xiong Lee","year":"2021","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_42_1","volume-title":"Inference with Reference: Lossless Acceleration of Large Language Models. arXiv:2304.04487","author":"Yang Nan","year":"2023","unstructured":"Nan Yang, Tao Ge, Liang Wang, Binxing Jiao, Daxin Jiang, Linjun Yang, Rangan Majumder, and Furu Wei. 2023. Inference with Reference: Lossless Acceleration of Large Language Models. arXiv:2304.04487 (2023)."},{"key":"e_1_3_2_1_43_1","volume-title":"A Survey of Large Language Models. arXiv:2303.18223","author":"Zhao Wayne Xin","year":"2023","unstructured":"Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Z. Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jianyun Nie, and Ji rong Wen. 2023. A Survey of Large Language Models. arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592047"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657951","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:39:25Z","timestamp":1755841165000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657951"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":44,"alternative-id":["10.1145\/3626772.3657951","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657951","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}