{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:40:01Z","timestamp":1755866401482,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":74,"publisher":"ACM","funder":[{"name":"NSF","award":["IIS-2225942"],"award-info":[{"award-number":["IIS-2225942"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730227","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:38:52Z","timestamp":1752457132000},"page":"2987-2993","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Low-Cost Document Retrieval with Dense Pseudo-Query Encoding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8581-6733","authenticated-orcid":false,"given":"Shanxiu","family":"He","sequence":"first","affiliation":[{"name":"University of California, Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7870-3100","authenticated-orcid":false,"given":"Wentai","family":"Xie","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5717-2637","authenticated-orcid":false,"given":"Yifan","family":"Qiao","sequence":"additional","affiliation":[{"name":"Apple Inc., Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-5088","authenticated-orcid":false,"given":"Parker","family":"Carlson","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1902-3387","authenticated-orcid":false,"given":"Tao","family":"Yang","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.05.009"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657769"},{"key":"e_1_3_2_1_3_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. NIPS","author":"Campos Daniel Fernando","year":"2016","unstructured":"Daniel Fernando Campos, Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, Li Deng, and Bhaskar Mitra. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. NIPS (2016)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730183"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.4"},{"key":"e_1_3_2_1_6_1","volume-title":"Overview of the TREC 2020 Deep Learning Track. ArXiv","volume":"2102","author":"Craswell Nick","year":"2020","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Fernando Campos, and Ellen M. Voorhees. 2020. Overview of the TREC 2020 Deep Learning Track. ArXiv, Vol. abs\/2102.07662 (2020)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401204"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148200"},{"key":"e_1_3_2_1_9_1","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2025. The Faiss library. arxiv: 2401.08281 [cs.LG] https:\/\/arxiv.org\/abs\/2401.08281"},{"key":"e_1_3_2_1_10_1","volume-title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. ArXiv","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, C. Lassance, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021a. SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. ArXiv, Vol. abs\/2109.10086 (2021)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531857"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3634912"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.241"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.379"},{"key":"e_1_3_2_1_16_1","unstructured":"Zhichao Geng Dongyu Ru and Yang Yang. 2024. Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers. arxiv: 2411.04403 [cs.IR] https:\/\/arxiv.org\/abs\/2411.04403"},{"key":"e_1_3_2_1_17_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan Amy Yang Angela Fan Anirudh Goyal"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0306-4573(00)00015-7"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657862"},{"key":"e_1_3_2_1_23_1","volume-title":"Dense Passage Retrieval for Open-Domain Question Answering. EMNLP'2020","volume":"2010","author":"Karpukhin V.","year":"2020","unstructured":"V. Karpukhin, Barlas O\u011fuz, Sewon Min, Patrick Lewis, Ledell Yu Wu, Sergey Edunov, Danqi Chen, and Wen tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. EMNLP'2020, Vol. ArXiv abs\/2010.08191 (2020)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591715"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531833"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591941"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511955"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.226"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3570724"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531884"},{"key":"e_1_3_2_1_31_1","volume-title":"TPRF: A Transformer-based Pseudo-Relevance Feedback Model for Efficient and Effective Retrieval. arxiv: 2401.13509 [cs.IR] https:\/\/arxiv.org\/abs\/2401.13509","author":"Li Hang","year":"2024","unstructured":"Hang Li, Chuting Yu, Ahmed Mourad, Bevan Koopman, and Guido Zuccon. 2024. TPRF: A Transformer-based Pseudo-Relevance Feedback Model for Efficient and Effective Retrieval. arxiv: 2401.13509 [cs.IR] https:\/\/arxiv.org\/abs\/2401.13509"},{"key":"e_1_3_2_1_32_1","volume-title":"Lin and Xueguang Ma","author":"Jimmy","year":"2021","unstructured":"Jimmy J. Lin and Xueguang Ma. 2021. A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques. ArXiv, Vol. abs\/2106.14807 (2021)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.17"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1645953.1646259"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Sean MacAvaney F. Nardini R. Perego N. Tonellotto Nazli Goharian and O. Frieder. 2020. Efficient Document Re-Ranking for Transformers by Precomputing Term Representations. SIGIR (2020).","DOI":"10.1145\/3397271.3401093"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557231"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331317"},{"key":"e_1_3_2_1_39_1","first-page":"2830","volume-title":"Accelerating Learned Sparse Indexes Via Term Impact Decomposition. In Findings of the Association for Computational Linguistics: EMNLP","author":"Mackenzie Joel","year":"2022","unstructured":"Joel Mackenzie, Antonio Mallia, Alistair Moffat, and Matthias Petri. 2022. Accelerating Learned Sparse Indexes Via Term Impact Decomposition. In Findings of the Association for Computational Linguistics: EMNLP 2022, Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang (Eds.). ACL, Abu Dhabi, United Arab Emirates, 2830-2842."},{"key":"e_1_3_2_1_40_1","article-title":"Anytime Ranking on Document-Ordered Indexes","volume":"40","author":"Mackenzie Joel","year":"2021","unstructured":"Joel Mackenzie, Matthias Petri, and Alistair Moffat. 2021. Anytime Ranking on Document-Ordered Indexes. ACM Trans. Inf. Syst., Vol. 40, 1, Article 13 (sep 2021), 32 pages.","journal-title":"ACM Trans. Inf. Syst."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_42_1","volume-title":"Learning Passage Impacts for Inverted Indexes. SIGIR","author":"Mallia Antonio","year":"2021","unstructured":"Antonio Mallia, O. Khattab, Nicola Tonellotto, and Torsten Suel. 2021. Learning Passage Impacts for Inverted Indexes. SIGIR (2021)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531774"},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the Open-Source IR Replicability Challenge","author":"Mallia Antonio","year":"2019","unstructured":"Antonio Mallia, Michal Siedlaczek, Joel Mackenzie, and Torsten Suel. 2019. PISA: Performant indexes and search for academia. Proceedings of the Open-Source IR Replicability Challenge (2019)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657906"},{"key":"e_1_3_2_1_46_1","unstructured":"Meta. 2024. Llama 3.2: Revolutionizing edge AI and vision with open customizable models. https:\/\/ai.meta.com\/blog\/llama-3-2-connect-2024-vision-edge-mobile-devices\/. https:\/\/ai.meta.com\/blog\/llama-3-2-connect-2024-vision-edge-mobile-devices\/"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277796"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1101"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592051"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583497"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.224"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_53_1","volume-title":"NAACL'22","volume":"2112","author":"Santhanam Keshav","year":"2022","unstructured":"Keshav Santhanam, O. Khattab, Jon Saad-Falcon, Christopher Potts, and Matei A. Zaharia. 2022. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. NAACL'22, Vol. ArXiv abs\/2112.01488 (2022)."},{"key":"e_1_3_2_1_54_1","volume-title":"LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PfpEtB3-csK","author":"Shen Tao","year":"2023","unstructured":"Tao Shen, Xiubo Geng, Chongyang Tao, Can Xu, Xiaolong Huang, Binxing Jiao, Linjun Yang, and Daxin Jiang. 2023. LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PfpEtB3-csK"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657861"},{"key":"e_1_3_2_1_56_1","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). https:\/\/openreview.net\/forum?id=wCu6T5xFjeJ"},{"key":"e_1_3_2_1_57_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arxiv: 2307.09288 [cs.CL] https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_1_58_1","volume-title":"SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval. ACL","author":"Wang Liang","year":"2023","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2023b. SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval. ACL (2023)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103026"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572405"},{"key":"e_1_3_2_1_61_1","unstructured":"Jie Xiao Qianyi Huang Xu Chen and Chen Tian. 2024. Large Language Model Performance Benchmarking on Mobile Platforms: A Thorough Evaluation. arxiv: 2410.03613 [cs.LG] https:\/\/arxiv.org\/abs\/2410.03613"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531799"},{"key":"e_1_3_2_1_63_1","volume-title":"RetroMAE: Pre-training Retrieval-oriented Transformers via Masked Auto-Encoder. EMNLP","author":"Xiao Shitao","year":"2022","unstructured":"Shitao Xiao, Zheng Liu, Yingxia Shao, and Zhao Cao. 2022b. RetroMAE: Pre-training Retrieval-oriented Transformers via Masked Auto-Encoder. EMNLP (2022)."},{"key":"e_1_3_2_1_64_1","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 ICLR."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/333135.333138"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657972"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"crossref","unstructured":"Yingrui Yang Yifan Qiao and Tao Yang. 2022. Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking. In ACL.","DOI":"10.18653\/v1\/2022.acl-long.51"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482124"},{"key":"e_1_3_2_1_69_1","volume-title":"Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance. CIKM","author":"Zhan Jingtao","year":"2021","unstructured":"Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2021a. Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance. CIKM (2021)."},{"key":"e_1_3_2_1_70_1","volume-title":"Optimizing Dense Retrieval Model Training with Hard Negatives. CoRR","author":"Zhan Jingtao","year":"2021","unstructured":"Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2021b. Optimizing Dense Retrieval Model Training with Hard Negatives. CoRR, Vol. abs\/2104.08051 (2021). https:\/\/arxiv.org\/abs\/2104.08051"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498443"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592047"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.250"},{"key":"e_1_3_2_1_74_1","unstructured":"Shengyao Zhuang and G. Zuccon. 2021. Fast Passage Re-ranking with Contextualized Exact Term Matching and Efficient Passage Expansion. ArXiv Vol. abs\/2108.08513 (2021)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Padua Italy","acronym":"SIGIR '25"},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:07:56Z","timestamp":1755864476000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730227"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":74,"alternative-id":["10.1145\/3726302.3730227","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730227","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}