{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T05:02:22Z","timestamp":1791867742046,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":57,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"QCLZD202301"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657743","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"1339-1349","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Scaling Laws For Dense Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3538-189X","authenticated-orcid":false,"given":"Yan","family":"Fang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University & Quan Cheng Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7253-5245","authenticated-orcid":false,"given":"Jingtao","family":"Zhan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University & Quan Cheng Laboratory, 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 & Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8718-9402","authenticated-orcid":false,"given":"Weihang","family":"Su","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University & Quan Cheng Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0957-1744","authenticated-orcid":false,"given":"Jia","family":"Chen","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc, 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":"Department of Computer Science and Technology, Tsinghua University & Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_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_2_1","first-page":"143","article-title":"Zipf's law and the Internet","volume":"3","author":"Adamic Lada A","year":"2002","unstructured":"Lada A Adamic and Bernardo A Huberman. 2002. Zipf's law and the Internet. Glottometrics, Vol. 3, 1 (2002), 143--150.","journal-title":"Glottometrics"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3624918.3625333"},{"key":"e_1_3_2_1_4_1","volume-title":"Understanding Scaling Laws for Recommendation Models. arXiv preprint arXiv:2208.08489","author":"Ardalani Newsha","year":"2022","unstructured":"Newsha Ardalani, Carole-Jean Wu, Zeliang Chen, Bhargav Bhushanam, and Adnan Aziz. 2022. Understanding Scaling Laws for Recommendation Models. arXiv preprint arXiv:2208.08489 (2022)."},{"key":"e_1_3_2_1_5_1","first-page":"1","article-title":"Semantic Models for the First-Stage Retrieval","volume":"40","author":"Cai Yinqiong","year":"2021","unstructured":"Yinqiong Cai, Yixing Fan, Jiafeng Guo, Fei Sun, Ruqing Zhang, and Xueqi Cheng. 2021. Semantic Models for the First-Stage Retrieval: A Comprehensive Review. ACM Transactions on Information Systems (TOIS) , Vol. 40 (2021), 1 -- 42. https:\/\/api.semanticscholar.org\/CorpusID:232147859","journal-title":"A Comprehensive Review. ACM Transactions on Information Systems (TOIS)"},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Machine Learning. PMLR, 4057--4086","author":"Clark Aidan","year":"2022","unstructured":"Aidan Clark, Diego De Las Casas, Aurelia Guy, Arthur Mensch, Michela Paganini, Jordan Hoffmann, Bogdan Damoc, Blake Hechtman, Trevor Cai, Sebastian Borgeaud, et al. 2022. Unified scaling laws for routed language models. In International Conference on Machine Learning. PMLR, 4057--4086."},{"key":"e_1_3_2_1_7_1","volume-title":"Manning","author":"Clark Kevin","year":"2020","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. In ICLR. https:\/\/openreview.net\/pdf?id=r1xMH1BtvB"},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning. PMLR, 7480--7512","author":"Dehghani Mostafa","year":"2023","unstructured":"Mostafa Dehghani, Josip Djolonga, Basil Mustafa, Piotr Padlewski, Jonathan Heek, Justin Gilmer, Andreas Peter Steiner, Mathilde Caron, Robert Geirhos, Ibrahim Alabdulmohsin, et al. 2023. Scaling vision transformers to 22 billion parameters. In International Conference on Machine Learning. PMLR, 7480--7512."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19--1423"},{"key":"e_1_3_2_1_10_1","volume-title":"Understanding emergent abilities of language models from the loss perspective. arXiv preprint arXiv:2403.15796","author":"Du Zhengxiao","year":"2024","unstructured":"Zhengxiao Du, Aohan Zeng, Yuxiao Dong, and Jie Tang. 2024. Understanding emergent abilities of language models from the loss perspective. arXiv preprint arXiv:2403.15796 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"SPLADE v2: Sparse lexical and expansion model for information retrieval. arXiv preprint arXiv:2109.10086","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Carlos Lassance, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021a. SPLADE v2: Sparse lexical and expansion model for information retrieval. arXiv preprint arXiv:2109.10086 (2021)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Machine Learning. PMLR, 10835--10866","author":"Gao Leo","year":"2023","unstructured":"Leo Gao, John Schulman, and Jacob Hilton. 2023. Scaling laws for reward model overoptimization. In International Conference on Machine Learning. PMLR, 10835--10866."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44686-9_33"},{"key":"e_1_3_2_1_17_1","volume-title":"Yang Yang, and Yanqi Zhou.","author":"Hestness Joel","year":"2017","unstructured":"Joel Hestness, Sharan Narang, Newsha Ardalani, Gregory Diamos, Heewoo Jun, Hassan Kianinejad, Md Mostofa Ali Patwary, Yang Yang, and Yanqi Zhou. 2017. Deep learning scaling is predictable, empirically. arXiv preprint arXiv:1712.00409 (2017)."},{"key":"e_1_3_2_1_18_1","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch Elena Buchatskaya Trevor Cai Eliza Rutherford Diego de las Casas Lisa Anne Hendricks Johannes Welbl Aidan Clark Tom Hennigan Eric Noland Katherine Millican George van den Driessche Bogdan Damoc Aurelia Guy Simon Osindero Karen Simonyan Erich Elsen Oriol Vinyals Jack William Rae and Laurent Sifre. 2022. An empirical analysis of compute-optimal large language model training. In Advances in Neural Information Processing Systems Alice H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=iBBcRUlOAPR"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 113--122","author":"Sebastian","year":"2021","unstructured":"Sebastian Hofst\"atter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin, and Allan Hanbury. 2021. Efficiently teaching an effective dense retriever with balanced topic aware sampling. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 113--122."},{"key":"e_1_3_2_1_20_1","volume-title":"Unsupervised Dense Information Retrieval with Contrastive Learning. Transactions on Machine Learning Research","author":"Izacard Gautier","year":"2022","unstructured":"Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2022. Unsupervised Dense Information Retrieval with Contrastive Learning. Transactions on Machine Learning Research (2022). https:\/\/openreview.net\/forum?id=jKN1pXi7b0"},{"key":"e_1_3_2_1_21_1","volume-title":"International conference on machine learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904--4916."},{"key":"e_1_3_2_1_22_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1080\/09296170802514153"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02181-7"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0014139"},{"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","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.92"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531772"},{"key":"e_1_3_2_1_31_1","first-page":"1","article-title":"Incorporating Structural Information into Legal Case Retrieval","volume":"42","author":"Ma Yixiao","year":"2023","unstructured":"Yixiao Ma, Yueyue Wu, Qingyao Ai, Yiqun Liu, Yunqiu Shao, Min Zhang, and Shaoping Ma. 2023. Incorporating Structural Information into Legal Case Retrieval. ACM Transactions on Information Systems , Vol. 42, 2 (2023), 1--28.","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463030"},{"key":"e_1_3_2_1_33_1","volume-title":"Pareto distributions and Zipf's law. Contemporary physics","author":"Newman Mark EJ","year":"2005","unstructured":"Mark EJ Newman. 2005. Power laws, Pareto distributions and Zipf's law. Contemporary physics, Vol. 46, 5 (2005), 323--351."},{"key":"e_1_3_2_1_34_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. In CoCo@ NIPS.","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A human generated machine reading comprehension dataset. In CoCo@ NIPS."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.669"},{"key":"e_1_3_2_1_36_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_37_1","volume-title":"Document expansion by query prediction. arXiv preprint arXiv:1904.08375","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Jimmy Lin, and Kyunghyun Cho. 2019b. Document expansion by query prediction. arXiv preprint arXiv:1904.08375 (2019)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126658"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_1_40_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_41_1","volume-title":"International Conference on Machine Learning. PMLR, 28492--28518","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning. PMLR, 28492--28518."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.77"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_24"},{"key":"e_1_3_2_1_44_1","volume-title":"No parameter left behind: How distillation and model size affect zero-shot retrieval. arXiv preprint arXiv:2206.02873","author":"Rosa Guilherme Moraes","year":"2022","unstructured":"Guilherme Moraes Rosa, Luiz Bonifacio, Vitor Jeronymo, Hugo Abonizio, Marzieh Fadaee, Roberto Lotufo, and Rodrigo Nogueira. 2022. No parameter left behind: How distillation and model size affect zero-shot retrieval. arXiv preprint arXiv:2206.02873 (2022)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3569929"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19--1139"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.168"},{"key":"e_1_3_2_1_50_1","volume-title":"Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022. Emergent Abilities of Large Language Models. Transactions on Machine Learning Research (2022). https:\/\/openreview.net\/forum?id=yzkSU5zdwD Survey Certification."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.35"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591874"},{"key":"e_1_3_2_1_53_1","volume-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=zeFrfgyZln","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. https:\/\/openreview.net\/forum?id=zeFrfgyZln"},{"key":"e_1_3_2_1_54_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=-Aw0rrrPUF","author":"Zeng Aohan","year":"2023","unstructured":"Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, Weng Lam Tam, Zixuan Ma, Yufei Xue, Jidong Zhai, Wenguang Chen, Zhiyuan Liu, Peng Zhang, Yuxiao Dong, and Jie Tang. 2023. GLM-130B: An Open Bilingual Pre-trained Model. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=-Aw0rrrPUF"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462880"},{"key":"e_1_3_2_1_57_1","volume-title":"Wayne Xin Zhao, and Ji-Rong Wen","author":"Zhang Gaowei","year":"2023","unstructured":"Gaowei Zhang, Yupeng Hou, Hongyu Lu, Yu Chen, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Scaling Law of Large Sequential Recommendation Models. arXiv preprint arXiv:2311.11351 (2023)"}],"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\/3626772.3657743","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:29:19Z","timestamp":1755840559000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657743"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":57,"alternative-id":["10.1145\/3626772.3657743","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657743","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"}}]}}