{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T19:06:22Z","timestamp":1779131182075,"version":"3.51.4"},"reference-count":66,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"name":"Hong Kong Research Grants Council","award":["16210625"],"award-info":[{"award-number":["16210625"]}]},{"name":"Hong Kong Research Grants Council","award":["T43-513\\\/23-N"],"award-info":[{"award-number":["T43-513\\\/23-N"]}]},{"name":"HKUST-WeBank Joint Laboratory","award":["WEB24EG01"],"award-info":[{"award-number":["WEB24EG01"]}]},{"name":"HKUST-MetaXJoint Laboratory for Advanced AI Computing","award":["METAX24EG01"],"award-info":[{"award-number":["METAX24EG01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2026,5,18]]},"abstract":"<jats:p>In multi-vector retrieval, both queries and data are represented as sets of high-dimensional vectors, enabling finer-grained semantic matching and improving retrieval quality over single-vector approaches. However, its practical adoption is held back by the lack of effective indexing algorithms. Existing work, attempting to reuse standard single-vector indexes, often fails to preserve multi-vector semantics or remains slow. In this work, we present GEM, a native indexing framework for multi-vector representations. The core idea is to construct a proximity graph directly over vector sets, preserving their fine-grained semantics while enabling efficient navigation. First, GEM designs a set-level clustering scheme. It associates each vector set with only its most informative clusters, effectively reducing redundancy without hurting semantic coverage. Then, it builds local proximity graphs within clusters and bridges them into a globally navigable structure. To handle the non-metric nature of multi-vector similarity, GEM decouples the graph construction metric from the final relevance score and injects semantic shortcuts to guide efficient navigation toward relevant regions. At query time, GEM launches beam search from multiple entry points and prunes paths early using cluster cues. To further enhance efficiency, a quantized distance estimation technique is used for both indexing and search. Across in-domain, out-of-domain, and multi-modal benchmarks, GEM achieves up to 16\u00d7 speedup over state-of-the-art methods while matching or improving accuracy.<\/jats:p>","DOI":"10.1145\/3802065","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T18:19:16Z","timestamp":1779128356000},"page":"1-27","source":"Crossref","is-referenced-by-count":0,"title":["GEM: A Native Graph-based Index for Multi-Vector Retrieval"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6876-5059","authenticated-orcid":false,"given":"Yao","family":"Tian","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7673-7311","authenticated-orcid":false,"given":"Zhoujin","family":"Tian","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3240-8225","authenticated-orcid":false,"given":"Xi","family":"Zhao","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-7387","authenticated-orcid":false,"given":"Ruiyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hong Kong Generative AI Research &amp;#38; Development Center, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6343-1455","authenticated-orcid":false,"given":"Xiaofang","family":"Zhou","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Earth mover distance over high-dimensional spaces","author":"Andoni Alexandr","unstructured":"Alexandr Andoni, Piotr Indyk, and Robert Krauthgamer. 2008. Earth mover distance over high-dimensional spaces. In SODA. SIAM, 343-352."},{"key":"e_1_2_1_2_1","first-page":"4772","article-title":"Reward Optimizing Recommendation using Deep Learning and Fast Maximum Inner Product Search","author":"Aouali Imad","year":"2022","unstructured":"Imad Aouali, Amine Benhalloum, Martin Bompaire, Achraf Ait Sidi Hammou, Sergey Ivanov, Benjamin Heymann, David Rohde, Otmane Sakhi, Flavian Vasile, and Maxime Vono. 2022. Reward Optimizing Recommendation using Deep Learning and Fast Maximum Inner Product Search. In KDD. ACM, 4772-4773.","journal-title":"KDD. ACM"},{"key":"e_1_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Ainesh Bakshi Piotr Indyk Rajesh Jayaram Sandeep Silwal and Erik Waingarten. 2023. Near-Linear Time Algorithm for the Chamfer Distance. In NeurIPS.","DOI":"10.52202\/075280-2918"},{"key":"e_1_2_1_4_1","volume-title":"Man Lung Yiu, and Bo Tang","author":"Bian Zheng","year":"2025","unstructured":"Zheng Bian, Man Lung Yiu, and Bo Tang. 2025. IGP: Efficient Multi-Vector Retrieval via Proximity Graph Index (SIGIR '25). Association for Computing Machinery, New York, NY, USA, 2524\u20132533."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"e_1_2_1_6_1","first-page":"253","article-title":"Locality-sensitive hashing scheme based on p-stable distributions","author":"Datar Mayur","year":"2004","unstructured":"Mayur Datar, Nicole Immorlica, Piotr Indyk, and Vahab S. Mirrokni. 2004. Locality-sensitive hashing scheme based on p-stable distributions. In SCG. ACM, 253-262.","journal-title":"SCG. ACM"},{"key":"e_1_2_1_7_1","volume-title":"DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries. In NeurIPS.","author":"Engels Joshua","year":"2023","unstructured":"Joshua Engels, Benjamin Coleman, Vihan Lakshman, and Anshumali Shrivastava. 2023. DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries. In NeurIPS."},{"key":"e_1_2_1_8_1","first-page":"257","article-title":"A White Box Analysis of ColBERT. In ECIR (2) (Lecture Notes in Computer Science, Vol. 12657)","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021. A White Box Analysis of ColBERT. In ECIR (2) (Lecture Notes in Computer Science, Vol. 12657). Springer, 257-263.","journal-title":"Springer"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/3303753.3303754"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3725413"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654970"},{"key":"e_1_2_1_12_1","volume-title":"Retrieval-Augmented Generation for Large Language Models: A Survey. CoRR","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Qianyu Guo, Meng Wang, and Haofen Wang. 2023. Retrieval-Augmented Generation for Large Language Models: A Survey. CoRR, Vol. abs\/2312.10997 (2023)."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.240"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0068"},{"key":"e_1_2_1_15_1","first-page":"737","article-title":"Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reduction","author":"Hofst\u00e4tter Sebastian","year":"2022","unstructured":"Sebastian Hofst\u00e4tter, Omar Khattab, Sophia Althammer, Mete Sertkan, and Allan Hanbury. 2022. Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reduction. In CIKM. ACM, 737-747.","journal-title":"CIKM. ACM"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850469.2850470"},{"key":"e_1_2_1_17_1","volume-title":"MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding. In NeurIPS.","author":"Jayaram Rajesh","year":"2024","unstructured":"Rajesh Jayaram, Laxman Dhulipala, Majid Hadian, Jason Lee, and Vahab Mirrokni. 2024. MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding. In NeurIPS."},{"key":"e_1_2_1_18_1","volume-title":"Ravishankar Krishnawamy, and Rohan Kadekodi.","author":"Subramanya Suhas Jayaram","year":"2019","unstructured":"Suhas Jayaram Subramanya, Fnu Devvrit, Harsha Vardhan Simhadri, Ravishankar Krishnawamy, and Rohan Kadekodi. 2019. Diskann: Fast accurate billion-point nearest neighbor search on a single node. Advances in neural information processing Systems, Vol. 32 (2019)."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Jyun-Yu Jiang Patrick H. Chen Cho-Jui Hsieh and Wei Wang. 2020. Clustering and Constructing User Coresets to Accelerate Large-scale Top-K Recommender Systems. In WWW. ACM \/ IW3C2 2177-2187.","DOI":"10.1145\/3366423.3380283"},{"key":"e_1_2_1_21_1","first-page":"6769","article-title":"Dense Passage Retrieval for Open-Domain Question Answering. In EMNLP (1)","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In EMNLP (1). Association for Computational Linguistics, 6769-6781.","journal-title":"Association for Computational Linguistics"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00405"},{"key":"e_1_2_1_23_1","first-page":"27670","article-title":"Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval","author":"Khattab Omar","year":"2021","unstructured":"Omar Khattab, Christopher Potts, and Matei A. Zaharia. 2021b. Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval. In NeurIPS. 27670-27682.","journal-title":"NeurIPS."},{"key":"e_1_2_1_24_1","first-page":"39","article-title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","author":"Khattab Omar","year":"2020","unstructured":"Omar Khattab and Matei Zaharia. 2020. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT. In SIGIR. ACM, 39-48.","journal-title":"SIGIR. ACM"},{"key":"e_1_2_1_25_1","volume-title":"Tao Lei, Iftekhar Naim, Ming-Wei Chang, and Vincent Zhao.","author":"Lee Jinhyuk","year":"2023","unstructured":"Jinhyuk Lee, Zhuyun Dai, Sai Meher Karthik Duddu, Tao Lei, Iftekhar Naim, Ming-Wei Chang, and Vincent Zhao. 2023. Rethinking the Role of Token Retrieval in Multi-Vector Retrieval. In NeurIPS."},{"key":"e_1_2_1_26_1","volume-title":"SIGMOD Conference. ACM, 2589-2599","author":"Lei Yifan","unstructured":"Yifan Lei, Qiang Huang, Mohan S. Kankanhalli, and Anthony K. H. Tung. 2020. Locality-Sensitive Hashing Scheme based on Longest Circular Co-Substring. In SIGMOD Conference. ACM, 2589-2599."},{"key":"e_1_2_1_27_1","unstructured":"Patrick S. H. Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel Sebastian Riedel and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In NeurIPS."},{"key":"e_1_2_1_28_1","first-page":"19730","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In ICML (Proceedings of Machine Learning Research, Vol. 202)","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven C. H. Hoi. 2023a. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In ICML (Proceedings of Machine Learning Research, Vol. 202). PMLR, 19730-19742.","journal-title":"PMLR"},{"key":"e_1_2_1_29_1","volume-title":"CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval. In ACL (1)","author":"Li Minghan","year":"2023","unstructured":"Minghan Li, Sheng-Chieh Lin, Barlas Oguz, Asish Ghoshal, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, and Xilun Chen. 2023b. CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval. In ACL (1). Association for Computational Linguistics, 11891-11907."},{"key":"e_1_2_1_30_1","first-page":"4428","article-title":"Learning Cross-Lingual IR from an English Retriever","author":"Li Yulong","year":"2022","unstructured":"Yulong Li, Martin Franz, Md. Arafat Sultan, Bhavani Iyer, Young-Suk Lee, and Avirup Sil. 2022. Learning Cross-Lingual IR from an English Retriever. In NAACL-HLT. Association for Computational Linguistics, 4428-4436.","journal-title":"NAACL-HLT. Association for Computational Linguistics"},{"key":"e_1_2_1_31_1","unstructured":"Weizhe Lin Jinghong Chen Jingbiao Mei Alexandru Coca and Bill Byrne. 2023. Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering. In NeurIPS."},{"key":"e_1_2_1_32_1","first-page":"5294","article-title":"PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers. In ACL (1)","author":"Lin Weizhe","year":"2024","unstructured":"Weizhe Lin, Jingbiao Mei, Jinghong Chen, and Bill Byrne. 2024. PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers. In ACL (1). Association for Computational Linguistics, 5294-5316.","journal-title":"Association for Computational Linguistics"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-020-00635-4"},{"key":"e_1_2_1_34_1","volume-title":"POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval. CoRR","author":"Liu Yaoyang","year":"2025","unstructured":"Yaoyang Liu, Junlin Li, Yinjun Wu, and Zhen Chen. 2025. POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval. CoRR, Vol. abs\/2505.19189 (2025)."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397240"},{"key":"e_1_2_1_36_1","first-page":"636","article-title":"MS-Shift: An Analysis of MS MARCO Distribution Shifts on Neural Retrieval. In ECIR (1) (Lecture Notes in Computer Science, Vol. 13980)","author":"Lupart Simon","year":"2023","unstructured":"Simon Lupart, Thibault Formal, and St\u00e9phane Clinchant. 2023. MS-Shift: An Analysis of MS MARCO Distribution Shifts on Neural Retrieval. In ECIR (1) (Lecture Notes in Computer Science, Vol. 13980). Springer, 636-652.","journal-title":"Springer"},{"key":"e_1_2_1_37_1","first-page":"208","article-title":"Image similarity search with compact data structures","author":"Lv Qin","year":"2004","unstructured":"Qin Lv, Moses Charikar, and Kai Li. 2004. Image similarity search with compact data structures. In CIKM. ACM, 208-217.","journal-title":"CIKM. ACM"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1217935.1217966"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_2_1_40_1","volume-title":"Cafarella","author":"Moll Oscar R.","year":"2023","unstructured":"Oscar R. Moll, Manuel Favela, Samuel Madden, Vijay Gadepally, and Michael J. Cafarella. 2023. SeeSaw: Interactive Ad-hoc Search Over Image Databases. Proc. ACM Manag. Data, Vol. 1, 4 (2023), 260:1-260:26."},{"key":"e_1_2_1_41_1","volume-title":"Zanoni Dias, and Ricardo da Silva Torres.","author":"Javier Alvaro","year":"2019","unstructured":"Javier Alvaro Vargas Mu n, oz, Marcos Andr\u00e9 Gon\u00e7alves, Zanoni Dias, and Ricardo da Silva Torres. 2019. Hierarchical Clustering-Based Graphs for Large Scale Approximate Nearest Neighbor Search. Pattern Recognit., Vol. 96 (2019)."},{"key":"e_1_2_1_42_1","first-page":"3","article-title":"Efficient Multi-vector Dense Retrieval with Bit Vectors. In ECIR (2) (Lecture Notes in Computer Science, Vol. 14609)","author":"Nardini Franco Maria","year":"2024","unstructured":"Franco Maria Nardini, Cosimo Rulli, and Rossano Venturini. 2024. Efficient Multi-vector Dense Retrieval with Bit Vectors. In ECIR (2) (Lecture Notes in Computer Science, Vol. 14609). Springer, 3-17.","journal-title":"Springer"},{"key":"e_1_2_1_43_1","volume-title":"Manning","author":"Paranjape Ashwin","year":"2022","unstructured":"Ashwin Paranjape, Omar Khattab, Christopher Potts, Matei Zaharia, and Christopher D. Manning. 2022. Hindsight: Posterior-guided training of retrievers for improved open-ended generation. In ICLR. OpenReview.net."},{"key":"e_1_2_1_44_1","volume-title":"Gonzalez","author":"Patil Shishir G.","year":"2023","unstructured":"Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. 2023. Gorilla: Large Language Model Connected with Massive APIs. CoRR, Vol. abs\/2305.15334 (2023)."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_2_1_46_1","unstructured":"Pinecone. 2025. Multi-vector embeddings tutorial. https:\/\/www.pinecone.io\/blog\/cascading-retrieval-with-multi-vector-representations\/"},{"key":"e_1_2_1_47_1","first-page":"19691","article-title":"Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval","author":"Reddy Arun","year":"2025","unstructured":"Arun Reddy, Alexander Martin, Eugene Yang, Andrew Yates, Kate Sanders, Kenton Murray, Reno Kriz, Celso M. de Melo, Benjamin Van Durme, and Rama Chellappa. 2025. Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval. In CVPR. Computer Vision Foundation \/ IEEE, 19691-19701.","journal-title":"CVPR. Computer Vision Foundation \/ IEEE"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026543900054"},{"key":"e_1_2_1_49_1","first-page":"1747","article-title":"PLAID","author":"Santhanam Keshav","year":"2022","unstructured":"Keshav Santhanam, Omar Khattab, Christopher Potts, and Matei Zaharia. 2022a. PLAID: An Efficient Engine for Late Interaction Retrieval. In CIKM. ACM, 1747-1756.","journal-title":"An Efficient Engine for Late Interaction Retrieval. In CIKM. ACM"},{"key":"e_1_2_1_50_1","first-page":"3715","article-title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","author":"Santhanam Keshav","year":"2022","unstructured":"Keshav Santhanam, Omar Khattab, Jon Saad-Falcon, Christopher Potts, and Matei Zaharia. 2022b. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. In NAACL-HLT. Association for Computational Linguistics, 3715-3734.","journal-title":"NAACL-HLT. Association for Computational Linguistics"},{"key":"e_1_2_1_51_1","first-page":"7500","article-title":"RELiC: Retrieving Evidence for Literary Claims. In ACL (1)","author":"Thai Katherine","year":"2022","unstructured":"Katherine Thai, Yapei Chang, Kalpesh Krishna, and Mohit Iyyer. 2022. RELiC: Retrieving Evidence for Literary Claims. In ACL (1). Association for Computational Linguistics, 7500-7518.","journal-title":"Association for Computational Linguistics"},{"key":"e_1_2_1_52_1","volume-title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In NeurIPS Datasets and Benchmarks.","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 NeurIPS Datasets and Benchmarks."},{"key":"e_1_2_1_53_1","first-page":"39","article-title":"Approximate Nearest Neighbor Search in High Dimensional Vector Databases: Current Research and Future Directions","volume":"47","author":"Tian Yao","year":"2023","unstructured":"Yao Tian, Ziyang Yue, Ruiyuan Zhang, Xi Zhao, Bolong Zheng, and Xiaofang Zhou. 2023b. Approximate Nearest Neighbor Search in High Dimensional Vector Databases: Current Research and Future Directions. IEEE Data Eng. Bull., Vol. 47, 3 (2023), 39-54.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_2_1_54_1","first-page":"2250","article-title":"DB-LSH","author":"Tian Yao","year":"2022","unstructured":"Yao Tian, Xi Zhao, and Xiaofang Zhou. 2022. DB-LSH: Locality-Sensitive Hashing with Query-based Dynamic Bucketing. In ICDE. IEEE, 2250-2262.","journal-title":"Locality-Sensitive Hashing with Query-based Dynamic Bucketing. In ICDE. IEEE"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3295831"},{"key":"e_1_2_1_56_1","first-page":"4924","article-title":"PASS","author":"Tian Zhoujin","year":"2023","unstructured":"Zhoujin Tian, Chaozhuo Li, Zhiqiang Zuo, Zengxuan Wen, Lichao Sun, Xinyue Hu, Wen Zhang, Haizhen Huang, Senzhang Wang, Weiwei Deng, Xing Xie, and Qi Zhang. 2023a. PASS: Personalized Advertiser-aware Sponsored Search. In KDD. ACM, 4924-4936.","journal-title":"Personalized Advertiser-aware Sponsored Search. In KDD. ACM"},{"key":"e_1_2_1_57_1","unstructured":"Vespa. 2024. Multi-vector embeddings tutorial. https:\/\/blog.vespa.ai\/announcing-long-context-colbert-in-vespa\/"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639269"},{"key":"e_1_2_1_59_1","first-page":"297","article-title":"Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval","author":"Wang Xiao","year":"2021","unstructured":"Xiao Wang, Craig Macdonald, Nicola Tonellotto, and Iadh Ounis. 2021. Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval. In ICTIR. ACM, 297-306.","journal-title":"ICTIR. ACM"},{"key":"e_1_2_1_60_1","first-page":"2552","article-title":"Reproducibility, Replicability, and Insights into Dense Multi-Representation Retrieval Models: from ColBERT to Col","author":"Wang Xiao","year":"2023","unstructured":"Xiao Wang, Craig Macdonald, Nicola Tonellotto, and Iadh Ounis. 2023. Reproducibility, Replicability, and Insights into Dense Multi-Representation Retrieval Models: from ColBERT to Col. In SIGIR. ACM, 2552-2561.","journal-title":"SIGIR. ACM"},{"key":"e_1_2_1_61_1","unstructured":"Weaviate. 2025. Multi-vector embeddings tutorial. https:\/\/docs.weaviate.io\/weaviate\/tutorials\/multi-vector-embeddings"},{"key":"e_1_2_1_62_1","unstructured":"Xiao Yang Kai Sun Hao Xin Yushi Sun Nikita Bhalla Xiangsen Chen Sajal Choudhary Rongze Daniel Gui Ziran Will Jiang Ziyu Jiang Lingkun Kong Brian Moran Jiaqi Wang Yifan Ethan Xu An Yan Chenyu Yang Eting Yuan Hanwen Zha Nan Tang Lei Chen Nicolas Scheffer Yue Liu Nirav Shah Rakesh Wanga Anuj Kumar Wen-tau Yih and Xin Luna Dong. 2024. CRAG - Comprehensive RAG Benchmark. CoRR Vol. abs\/2406.04744 (2024)."},{"key":"e_1_2_1_63_1","volume-title":"FILIP: Fine-grained Interactive Language-Image Pre-Training. In ICLR. OpenReview.net.","author":"Yao Lewei","year":"2022","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. 2022. FILIP: Fine-grained Interactive Language-Image Pre-Training. In ICLR. OpenReview.net."},{"key":"e_1_2_1_64_1","first-page":"2486","article-title":"Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models","author":"Zhan Jingtao","year":"2022","unstructured":"Jingtao Zhan, Xiaohui Xie, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2022. Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models. In CIKM. ACM, 2486-2496.","journal-title":"CIKM. ACM"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.14778\/3594512.3594527"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.14778\/3377369.3377374"}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3802065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T18:21:08Z","timestamp":1779128468000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3802065"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":66,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,18]]}},"alternative-id":["10.1145\/3802065"],"URL":"https:\/\/doi.org\/10.1145\/3802065","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]}}}