ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for document ranking. While remarkably effective, the ranking models based on these LMs increase computational cost by orders of magnitude over prior approaches, particularly as they must feed each query-document pair through a massive neural network to compute a single relevance score. To tackle this, we present ColBERT, a novel ranking model that adapts deep LMs (in particular, BERT) for efficient retrieval. ColBERT introduces a late interaction architecture that independently encodes the query and the document using BERT and then employs a cheap yet powerful interaction step that models their fine-grained similarity. By delaying and yet retaining this fine-granular interaction, ColBERT can leverage the expressiveness of deep LMs while simultaneously gaining the ability to pre-compute document representations offline, considerably speeding up query processing. Crucially, ColBERT's pruning-friendly interaction mechanism enables leveraging vector-similarity indexes for end-to-end retrieval directly from millions of documents. We extensively evaluate ColBERT using two recent passage search datasets. Results show that ColBERT's effectiveness is competitive with existing BERT-based models (and outperforms every non-BERT baseline), while executing two orders-of-magnitude faster and requiring up to four orders-of-magnitude fewer FLOPs per query.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The only ML component is a CrossEncoder reranker ( mxbai-rerank-large-v1 , 435M parameters, DeBERTaV3) fused with ColBERT (Khattab & Zaharia, 2020) via Reciprocal Rank Fusion (RRF), applied after retrieval is complete to prioritize passages before token-budget truncation.”
From SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval (2026) · cites this paper as Khattab & Zaharia, 2020
In the citing paper
“While dense retrievers like Dense Passage Retrieval (DPR) [14] and late-interaction models like ColBERT [15] improve recall on single-hop queries, they often struggle with multi-hop reasoning, where the answer depends on composing information from multiple disjoint documents [20, 6].”
From Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assembly (2025) · cites this paper as [15]
In the citing paper
“Research on retrieval optimization has explored multiple techniques, yet studies specifically focused on prefetching size in RaLM systems are still limited.”
From Exploring Optimal Prefetching Sizes in RaLMSpec to Enhance Retrieval-Augmented Generation Efficiency (2025) · cites this paper as [9]
In the citing paper
“Early RAG implementations, however, often relied on document retrieval methods that introduced noise and excessive context [26, 55, 60, 122].”
From LEGO-GraphRAG: Modularizing Graph-Based Retrieval-Augmented Generation for Design Space Exploration (2025) · cites this paper as [55]
In the citing paper
“Standard retrieval methods like RAG and MemoryBank (Zhong et al., 2024) rely fundamentally on vector similarity (Karpukhin et al., 2020; Khattab and Zaharia, 2020), representing memories as isolated points in embedding space (Hu et al., 2025). Consequently, they struggle with queries requiring causal bridging between semantically dissimilar or distant events (Yang et al., 2018; Qi et al., 2019; Tr”
From Synapse: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation (2026) · cites this paper as Khattab and Zaharia, 2020
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“At a high level, TK improves the KNRM architecture described earlier: while KNRM employs kernel pooling on top of word-embedding-based interaction, TK uses a Transformer [34] component for contextually encoding queries and documents before kernel pooling.”
MethodBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 2×
“Among them, a recent approach has emerged that ne-tunes deep pre-trained language models (LMs) like ELMo [29] and BERT [5] for estimating relevance.”
BackgroundGoogle's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jégou, H. (2017) · arXiv · doi:10.48550/arxiv.1702.08734 · Cited by 4,140 · cited 2×
“Additionally, it enables ColBERT to leverage vector-similarity search indexes (e.g., [1, 16]) to retrieve the top-k results directly from a large document collection, substantially improving recall over models that only re-rank the output of term-based retrieval.”
MethodMS MARCO: A Human Generated MAchine Reading COmprehension Dataset
Bajaj, P., Campos, D., Craswell, N., Deng, L., Gao, J., Liu, X., Majumder, R., McNamara, A., Mitra, B., Nguyen, T., et al. (2016) · arXiv · doi:10.48550/arxiv.1611.09268 · Cited by 2,473
Robertson, S. E., Walker, S., Jones, S., Hancock‐Beaulieu, M., & Gatford, M. (1994) · Text REtrieval Conference · Cited by 2,212
Learning deep structured semantic models for web search using clickthrough data
Huang, P.-S., He, X., Gao, J., Deng, L., Acero, A., & Heck, L. (2013) · Proceedings of the 22nd ACM international conference on Information & Knowledge Management · doi:10.1145/2505515.2505665 · Cited by 2,009 · cited 1×
“On the le, Figure 2 (a) illustrates representation-focused rankers, which independently compute an embedding for q and another for d and estimate relevance as a single similarity score between two vectors [13, 41].”
BackgroundTinyBERT: Distilling BERT for natural language understanding
Jiao, X., Yin, Y., Shang, L., Jiang, X., Chen, X., Li, L., Wang, F., & Liu, Q. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.372 · Cited by 1,786
A Deep Relevance Matching Model for Ad-hoc Retrieval
Guo, J., Fan, Y., Ai, Q., & Croft, W. B. (2016) · Proceedings of the 25th ACM International on Conference on Information and Knowledge Management · doi:10.1145/2983323.2983769 · Cited by 806 · cited 1×
“Over the past few years, the Information Retrieval (IR) community has witnessed the introduction of a host of neural ranking models, including DRMM [8], KNRM [5, 36], and Duet [21, 23].”
BackgroundNogueira, R., & Cho, K. (2019) · arXiv · doi:10.48550/arxiv.1901.04085 · Cited by 615 · cited 9×
“Similar to [25], we fine-tune all ColBERT models with learning rate 3 × 10 − 6 with a batch size 32.”
BackgroundMethodInfluential
Research works printed but not linked: 14
- Zhuyun Dai and Jamie Callan . 2019 a. Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval. arXiv preprint arXiv:1910.10687 ( 2019 ). Zhuyun Dai and Jamie Callan. 2019 a. Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval. arXiv preprint arXiv:1910.10687 (2019). · arXiv
- Zhuyun Dai and Jamie Callan . 2019 b. Deeper Text Understanding for IR with Contextual Neural Language Modeling. arXiv preprint arXiv:1905.09217 ( 2019 ). Zhuyun Dai and Jamie Callan. 2019 b. Deeper Text Understanding for IR with Contextual Neural Language Modeling. arXiv preprint arXiv:1905.09217 (2019). · arXiv
- Jiafeng Guo , Yixing Fan , Liang Pang , Liu Yang , Qingyao Ai , Hamed Zamani , Chen Wu , W Bruce Croft , and Xueqi Cheng . 2019. A deep look into neural ranking models for information retrieval. arXiv preprint arXiv:1903.06902 ( 2019 ). Jiafeng Guo, Yixing Fan, Liang Pang, Liu Yang, Qingyao Ai, Hamed Zamani, Chen Wu, W Bruce Croft, and Xueqi Cheng. 2019. A deep look into neural ranking models for information retrieval. arXiv preprint arXiv:1903.06902 (2019). · arXiv
- Sebastian Hofst"atter and Allan Hanbury . 2019. Let's measure run time! Extending the IR replicability infrastructure to include performance aspects. arXiv preprint arXiv:1907.04614 ( 2019 ). Sebastian Hofst"atter and Allan Hanbury. 2019. Let's measure run time! Extending the IR replicability infrastructure to include performance aspects. arXiv preprint arXiv:1907.04614 (2019). · arXiv
- Sebastian Hofst"atter, Markus Zlabinger , and Allan Hanbury . 2019 b. TU Wien@ TREC Deep Learning'19--Simple Contextualization for Re-ranking. arXiv preprint arXiv:1912.01385 ( 2019 ). Sebastian Hofst"atter, Markus Zlabinger, and Allan Hanbury. 2019 b. TU Wien@ TREC Deep Learning'19--Simple Contextualization for Re-ranking. arXiv preprint arXiv:1912.01385 (2019). · arXiv
- Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). · arXiv
- Bhaskar Mitra and Nick Craswell . 2019. An Updated Duet Model for Passage Re-ranking. arXiv preprint arXiv:1903.07666 ( 2019 ). Bhaskar Mitra and Nick Craswell. 2019. An Updated Duet Model for Passage Re-ranking. arXiv preprint arXiv:1903.07666 (2019). · arXiv
- Bhaskar Mitra , Corby Rosset , David Hawking , Nick Craswell , Fernando Diaz , and Emine Yilmaz . 2019. Incorporating query term independence assumption for efficient retrieval and ranking using deep neural networks. arXiv preprint arXiv:1907.03693 ( 2019 ). Bhaskar Mitra, Corby Rosset, David Hawking, Nick Craswell, Fernando Diaz, and Emine Yilmaz. 2019. Incorporating query term independence assumption for efficient retrieval and ranking using deep neural networks. arXiv preprint arXiv:1907.03693 (2019). · arXiv
- Rodrigo Nogueira , Wei Yang , Kyunghyun Cho , and Jimmy Lin . 2019 b. Multi-Stage Document Ranking with BERT. arXiv preprint arXiv:1910.14424 ( 2019 ). Rodrigo Nogueira, Wei Yang, Kyunghyun Cho, and Jimmy Lin. 2019 b. Multi-Stage Document Ranking with BERT. arXiv preprint arXiv:1910.14424 (2019). · arXiv
- Rodrigo Nogueira , Wei Yang , Jimmy Lin , and Kyunghyun Cho . 2019 c. Document Expansion by Query Prediction. arXiv preprint arXiv:1904.08375 ( 2019 ). Rodrigo Nogueira, Wei Yang, Jimmy Lin, and Kyunghyun Cho. 2019 c. Document Expansion by Query Prediction. arXiv preprint arXiv:1904.08375 (2019). · arXiv
- Matthew E Peters , Mark Neumann , Mohit Iyyer , Matt Gardner , Christopher Clark , Kenton Lee , and Luke Zettlemoyer . 2018. Deep contextualized word representations. arXiv preprint arXiv:1802.05365 ( 2018 ). Matthew E Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. arXiv preprint arXiv:1802.05365 (2018). · arXiv
- Yifan Qiao , Chenyan Xiong , Zhenghao Liu , and Zhiyuan Liu . 2019. Understanding the Behaviors of BERT in Ranking. arXiv preprint arXiv:1904.07531 ( 2019 ). Yifan Qiao, Chenyan Xiong, Zhenghao Liu, and Zhiyuan Liu. 2019. Understanding the Behaviors of BERT in Ranking. arXiv preprint arXiv:1904.07531 (2019). · arXiv
- Colin Raffel , Noam Shazeer , Adam Roberts , Katherine Lee , Sharan Narang , Michael Matena , Yanqi Zhou , Wei Li , and Peter J Liu . 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 ( 2019 ). Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 (2019). · arXiv
- Raphael Tang , Yao Lu , Linqing Liu , Lili Mou , Olga Vechtomova , and Jimmy Lin . 2019. Distilling task-specific knowledge from BERT into simple neural networks. arXiv preprint arXiv:1903.12136 ( 2019 ). Raphael Tang, Yao Lu, Linqing Liu, Lili Mou, Olga Vechtomova, and Jimmy Lin. 2019. Distilling task-specific knowledge from BERT into simple neural networks. arXiv preprint arXiv:1903.12136 (2019). · arXiv
Cited by
Items 701–800 of 1,023
No Query Left Behind: Query Refinement via Backtranslation
Rajaei, D., Taheri, Z., & Fani, H. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679729 · Cited by 4
“We acknowledge dense information retrieval methods like colbert [41] and their state-of-the-art retrieval performance.”
Galuščáková, P., Oard, D. W., & Nair, S. (2024) · ACM eBooks · doi:10.1145/3674127.3674136 · Cited by 3
Frihat, S., Papenmeier, A., & Fuhr, N. (2024) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/3677389.3702558 · Cited by 4
“The available medical search engines provide sophisticated similarity-based retrieval [28, 33].”
Token Pruning Optimization for Efficient Multi-vector Dense Retrieval
He, S., Al-Darabsah, M., Nair, S., May, J., Agarwal, T., Yang, T., & Teo, C. H. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88708-6_7 · Cited by 2
“ColBERT [12] with a multi-vector representation can be viewed as a middle-ground between the single-vector bi-encoder and the cross-encoder design.”
Exploring the Effectiveness of Multi-stage Fine-Tuning for Cross-Encoder Re-rankers
Pezzuti, F., MacAvaney, S., & Tonellotto, N. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88714-7_45 · Cited by 3
Lystbæk, M. S., & Lystbæk, U. S. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-96199-1_2 · Cited by 3
Refined Medical Search via Dense Retrieval and User Interaction
Goli, R., Moffat, A., & Buchanan, G. R. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730292 · Cited by 5
“A prominent example is Contextualized Late Interaction over BERT ( ColBERT ) [14], which employs a two-stage scoring mechanism.”
RE-AdaptIR: Improving Information Retrieval through Reverse Engineered Adaptation
Fleshman, W., & Durme, B. V. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730240 · Cited by 4
A GenAI System for Improved FAIR Independent Biological Database Integration
Sakib, S. N., Naha, K., Rubaiat, S. Y., & Jamil, H. M. (2025) · Journal of Data and Information Quality · doi:10.1145/3770753 · Cited by 2
“The following sections will explore the architecture and implementation of FAIRBridge, followed by a detailed evaluation of its performance and a discussion of its implications for the future of data-driven life sciences research.”
A Flexible and Scalable Framework for Video Moment Search
Zhang, C., Zhu, X., & Sun, A. (2025) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3767695.3769480 · Cited by 3
Yang, L., Li, D., Zheng, S., Kong, L., Li, M., Kong, F., & Wang, W. (2026) · Applied Sciences · doi:10.3390/app16115641 · Cited by 2
Deep neural ranking model using distributed smoothing
Pourbahman, Z., Momtazi, S., & Bagheri, A. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119913 · Cited by 3
Explicit and Implicit Semantic Ranking Framework
Zhu, X., Lin, T., Anand, V., Calderwood, M. D., Clausen-Brown, E., Lueck, G., Yim, W.-W., & Wu, C. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543873.3584621 · Cited by 2
“With the popularity of deep neural ranking models in learningto-rank [10, 22], contextual featurization using Transformer models such as BERT [5] and Big Bird [28] largely eliminate human eforts and achieve high performance in ColBERT [13], PARADE [15], MVA [29], and more [8, 12, 17].”
MethodFoundation Models for Text Generation
Paaß, G., & Giesselbach, S. (2023) · Artificial intelligence: foundations, theory, and algorithms/Artificial intelligence: Foundations, theory, and algorithms · doi:10.1007/978-3-031-23190-2_6 · Cited by 5
Brito, E., & Iser, H. (2023) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3539618.3592017 · Cited by 4
“Second, Khattab and Zaharia [8] use [MASK] tokens within the ColBERTv2 model for query expansion.”
MethodOptimizing Test-Time Query Representations for Dense Retrieval
Sung, M., Park, J., Kang, J., Chen, D., & Lee, J. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.354 · Cited by 16
“, 2021a) and information retrieval (Khattab and Zaharia, 2020; Xiong et al., 2020).”
BackgroundHierarchical Transformer-based Query by Multiple Documents
Huang, Z., Naseri, S., Bonab, H., Sarwar, S. M., & Allan, J. (2023) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3578337.3605130 · Cited by 3
“Inspired by the late-interaction scoring function [21, 22], we”
MethodInfluentialAnswer Retrieval for Math Questions Using Structural and Dense Retrieval
Zhong, W., Xie, Y., & Lin, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42448-9_18 · Cited by 2
Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval
Jiang, F., Xu, Q., Drummond, T. W., & Cohn, T. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.65 · Cited by 8
Relevance-assisted Generation for Robust Zero-shot Retrieval
Kim, J., Kim, M., Park, J., & Hwang, S.-W. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-industry.67 · Cited by 4
An Efficient Document Retrieval for Korean Open-Domain Question Answering Based on ColBERT
Kang, B., Kim, Y., & Shin, Y. (2023) · Applied Sciences · doi:10.3390/app132413177 · Cited by 3
Event-Specific Document Ranking Through Multi-stage Query Expansion Using an Event Knowledge Graph
Abdollahi, S., Kuculo, T., & Gottschalk, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56060-6_22 · Cited by 2
DESIRE-ME: Domain-Enhanced Supervised Information Retrieval Using Mixture-of-Experts
Kasela, P., Pasi, G., Perego, R., & Tonellotto, N. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56060-6_8 · Cited by 2
“A notable example is ColBERT [16], which computes contextualized token-level embeddings for both documents and queries and uses them at retrieval and scoring time.”
BackgroundDecoupled Transformer for Scalable Inference in Open-domain Question Answering
Facebook, ElFadeel, H., Peshterliev, S., & Facebook (2021) · International conference Recent advances in natural language processing · doi:10.26615/978-954-452-072-4_044 · Cited by 3
Enhancing Document Ranking with Task-adaptive Training and Segmented Token Recovery Mechanism
Sun, X., Cui, Y., Tang, H., Zhang, F., Jin, B., & Wang, S. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.289 · Cited by 2
GazBy: Gaze-Based BERT Model to Incorporate Human Attention in Neural Information Retrieval
Dong, S., Goldstein, J., & Yang, G. H. (2022) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3539813.3545129 · Cited by 3
I3: I ntent- I ntrospective Retrieval Conditioned on I nstructions
Pan, K., Li, J., Wang, W., Fei, H., Song, H., Ji, W., Lin, J., Liu, X., Chua, T., & Tang, S. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657745 · Cited by 18
“Dense retrieval [16, 17, 20, 51, 52] is widely adopted in information retrieval that demonstrates strong advantages over sparse retrieval methods [37].”
Self-supervised Answer Retrieval on Clinical NotesPreprint
Grundmann, P., Arnold, S., & Löser, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.00775 · Cited by 7
Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
Krishna, S., Krishna, K., Mohananey, A., Schwarcz, S., Stambler, A., Upadhyay, S., & Faruqui, M. (2024) · arXiv · doi:10.48550/arxiv.2409.12941 · Cited by 1
“This includes exploring dense retrievers trained directly on the multihop retrieval task, such as those based on ColBERT (Khattab and Zaharia, 2020), or SimCSE (Gao et al., 2021) architectures.”
MethodA Scientific Document Retrieval and Reordering Method by Incorporating HFS and LSD
Feng, Z., & Tian, X. (2023) · Applied Sciences · doi:10.3390/app132011207 · Cited by 1
TD-CRESTS: Top-Down Chunk Retrieval Based on Entity, Section, and Topic Selection
Landolsi, M. Y., & Romdhane, L. B. (2024) · Lecture notes in business information processing · doi:10.1007/978-3-031-59465-6_3 · Cited by 1
A Novel Centrality-Driven Clustering Approach for Information Retrieval and Question Answering
Edrees, Z., & Ortacki, Y. (2024) · International Artificial Intelligence and Data Processing Symposium (IDAP) · doi:10.1109/idap64064.2024.10711092 · Cited by 1
“When a user submits a query, BERT identifies pages that exhibit not only keyword matches but also a deeper level of semantic relevance [41], [42].”
BackgroundSimilarity Measurement Model for Standard Clauses Based on RAG
Yang, Y., Tang, W., Lu, Y., Wang, J., & Jiang, Y. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-4016-4_29 · Cited by 1
Optimized Spoken Query Cross-Lingual Document Retrieval using BM25 and Neural Re-Ranking with AdamW
Kaushish, A., Vijayvargiya, A., Rawat, K., Kumar, M., & Jain, V. (2025) · OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry (OTCON) · doi:10.1109/otcon65728.2025.11070333 · Cited by 1
“Recent neural re-ranking development has focused on enhancing efficiency and scalability, and models like ColBERT and Poly-encoder enable fine-grained interaction modeling without significant computational overhead [22].”
InfluentialProlog-RAG: A Symbolic Reasoning Approach to Retrieval-Augmented Generation
Zhang, B., Li, J., Peng, K., Zheng, S., & Meng, K. (2025) · International Conference on Computer Engineering and Application (ICCEA) · doi:10.1109/iccea65460.2025.11103126 · Cited by 1
ViGPT Researcher: An AI-Powered Online Research Assistant for Comprehensive and In-Depth Analysis
Pham, T. T. T., Pham, P. H., Pham, V. H., Tran, H. M., & Duong, T. N. (2025) · International Conference on Applying New Technology in Green Buildings (ATiGB) · doi:10.1109/atigb66719.2025.11142107 · Cited by 1
“Studies by [7] introduced RAG as an effective framework for integrating external knowledge into generative models, while [8] improved document retrieval methods to further enhance accuracy in open-domain question answering tasks.”
HIM-RAG: A Heuristic Framework for Iterative Multi-Source Retrieval-Augmented Generation
Li, S., Yu, Y., Yang, H., Zhou, Y., & Ji, C. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229295 · Cited by 2
Deploying Vision Retrieval Augmented Generation as Assistant for xPPU Maintenance
Höfgen, J., Tran, N. T. H., Vogel-Heuser, B., Chen, P.-J., Wilch, J., Cheng, F.-T., & Hsieh, Y.-M. (2025) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case58245.2025.11164045 · Cited by 1
“The indexing module (b) employs deep learning–based encoding techniques, transforming textual maintenance documents into structured embeddings using Late Interaction and Softmax cross-entropy mechanisms [10].”
Hou, J., Finke, A., & Cosma, G. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3639808 · Cited by 2
“1: Breakdown (in the sense of performance degradation on retain and tests sets) of classical machine unlearning baselines in neural information retrieval.”
Boddupally, H. L. (2023) · International Journal of Scientific Research in Science Engineering and Technology · doi:10.32628/ijsrset232533 · Cited by 1
Comparison of Chunking Techniques Across Diverse Document Types in NLP Retrieval Tasks
Jaiswal, S., Bisht, P., Kansara, K., & Datta, M. S. (2025) · International Conference on Responsible, Generative and Explainable AI (ResGenXAI) · doi:10.1109/resgenxai64788.2025.11344045 · Cited by 1
Semantic Intent Weaver: A Context-Aware Search Algorithm for Ambiguous Query Resolution
Papachappa, H. M. (2026) · International Conference on Computational Intelligence in Data Science (ICCIDS) · doi:10.1109/iccids69108.2026.11407681 · Cited by 1
“This approach, treating session data as a short-term proxy for user intent, is a standard and validated technique in offline evaluations of context-aware systems where long-term user profiles are unavailable [20].”
UniEval-RAG: A Unified End-to-End Evaluation Framework for RAG Systems
Liang, S., Gong, X., Li, F., Zhou, H., Wu, Y., & Liao, C. (2025) · International Conference on Computer, Internet of Things and Smart City (CIoTSC) · doi:10.1109/ciotsc67482.2025.11412981 · Cited by 1
Smart Note Management Learning Hub
Kate, P., Dagadkar, S. N., & Sontakke, A. (2026) · International Conference on Mobile Computing and Sustainable Informatics (ICMCSI) · doi:10.1109/icmcsi67283.2026.11412869 · Cited by 1
An Auditable LLM-RAG Architecture for Financial Document Intelligence and Decision Support
Cosentino, C., Squillace, S., & Marozzo, F. (2026) · Future Internet · doi:10.3390/fi18060284 · Cited by 1
Almohammady, A., Alnanih, R. A., & Alowidi, N. (2026) · Applied Sciences · doi:10.3390/app16115482 · Cited by 1
Taking RAG Systems to the Next Level: Reasoning That Doesn't Blow Up Your Context
Lahmy, M., & Yozevitch, R. (2026) · IEEE Swiss Conference on Data Science (SDS) · doi:10.1109/sds70563.2026.00014 · Cited by 1
“While models like DPR [2] and ColBERT [8] improve recall, they struggle with multi-hop reasoning where answers require composing disjoint documents [9], [10].”
Ma, Y., Jiang, J., Wang, S., Liu, J., Qi, X., & Wang, X. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105126 · Cited by 2
Benchmarking Information Retrieval for Large Archives of Historical Documents
Steiner, T., Streilein, M., Fischer, A., & Riesen, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36039-7_4 · Cited by 1
CSurF: Sparse Lexical Retrieval through Contextualized Surface Forms
Fan, Z., Gao, L., & Callan, J. (2023) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3578337.3605126 · Cited by 1
ML-DPR: A Meta-Learning-Based Model for Domain-Adaptive Dense Passage Retrieval
Niu, J. (2023) · IEEE International Conference on Image Processing and Computer Applications (ICIPCA) · doi:10.1109/icipca59209.2023.10257843 · Cited by 1
“The listwise distillation greatly minimizes the gap between representation and interaction bert model compared to previous late-interaction method such as Colbert [10].”
MethodNoisy Self-Training with Synthetic Queries for Dense Retrieval
Jiang, F., Drummond, T. W., & Cohn, T. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.803 · Cited by 5
One-step Reach: LLM-based Keyword Generation for Sponsored Search Advertising
Wang, Y., Sha, Z., Lin, K., Feng, C., Zhu, K., Wang, L., Jiao, X., Huang, F., Ye, C., He, D., et al. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589335.3651943 · Cited by 1
“Initially, it retrieves a comprehensive set of keywords that are semantically relevant to the query from the global bidding space as fully as possible through literal or vector search techniques [3], and then exploits multiple strategies to judge the match type of the query-keyword pair among them.”
BackgroundOussaidene, S., Lhadj, L. S., & Boughanem, M. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0579-8_4 · Cited by 1
eCommerce Search and Discovery
Kallumadi, S. T., & King, T. H. (2024) · ACM eBooks · doi:10.1145/3674127.3674140 · Cited by 1
ContextualCoder: Adaptive In-Context Prompting for Programmatic Visual Question Answering
Shen, R., Inoue, N., Guan, D., Cai, R., Kot, A. C., & Shinoda, K. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3543043 · Cited by 5
Maybe You Are Looking for CroQS Cross-Modal Query Suggestion for Text-to-Image Retrieval
Pacini, G., Carrara, F., Messina, N., Tonellotto, N., Amato, G. M., & Falchi, F. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88711-6_9 · Cited by 1
Improving Low-Resource Retrieval Effectiveness Using Zero-Shot Linguistic Similarity Transfer
Chari, A., MacAvaney, S., & Ounis, I. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88717-8_22 · Cited by 6
MURR: Model Updating with Regularized Replay for Searching a Document Stream
Yang, E., Tonellotto, N., Lawrie, D., MacAvaney, S., Mayfield, J., Oard, D. W., & Miller, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88708-6_6 · Cited by 3
“Fine-tuning a query-document relevance model—such as a BERT cross-encoder [30] or a ColBERT dual encoder [19]—only once would not work well in such cases; some approach to periodic, incremental, or continuous updating is needed to reflect these changes.”
Retrieval-Augmented Generation of Event Collections from Web Archives and the Live Web
Abdollahi, S., Nejdl, W., & Gottschalk, S. (2025) · International Journal on Digital Libraries · doi:10.1007/s00799-025-00419-7 · Cited by 1
“Building upon BERT and other language models, models such as DuoBERT [30], PARADE [29], and ColBERT [55] introduce mechanisms like passage representation aggregation, multi-stage ranking, and late interaction to improve ranking effectiveness.”
Reverse-Engineering the Retrieval Process in GenIR Models
Reusch, A., & Belinkov, Y. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730076 · Cited by 5
Dynamic Margin-based Contrastive Learning for Robust Negative Sampling in Information Retrieval
Chen, T.-T., Wang, C., & Tsai, M.-F. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730182 · Cited by 1
ULP: Unlabeled Location Prediction from Text
He, X. Q., Liu, Y., Sun, Y., Xing, X., Lu, X., & Liu, Y. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730104 · Cited by 1
Exploring the Utility of Embedding Similarity for Contract Tasks
Donnelly, J., & Roegiest, A. (2025) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3731120.3744609 · Cited by 1
Zero-Shot and Hybrid Strategies for Tetun Ad-Hoc Text Retrieval
de Jesús, G., Singh, S., Nunes, S., & Yates, A. (2025) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3731120.3744593 · Cited by 3
Ensemble ToT and Its Application to Automatic Grading
Ito, Y., & Ma, Q. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02049-9_18 · Cited by 2
A knowledge-based approach for pseudo-relevance feedback by exploiting semantic relevance
Wang, J., Zeng, J., Huang, J. X., Wang, L., & Wang, J. (2025) · Knowledge and Information Systems · doi:10.1007/s10115-025-02581-5 · Cited by 2
Attimonelli, M., Bellis, A. D., Pomo, C., Jannach, D., Sciascio, E. D., & Noia, T. D. (2025) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3705328.3748040 · Cited by 7
“Despite the potential advantages of domain-specific fine-tuning, we find that GTEs can outperform fine-tuned models (e.g., BLaIR), classical architectures (e.g., ColBERT), and closed-source solutions (e.g., OpenAI) without task-specific adaptation.”
InfluentialHiPC-QR: Hierarchical Prompt Chaining for Query Reformulation
Yang, H., Li, H., & Gonçalves, T. (2025) · Information · doi:10.3390/info16090790 · Cited by 1
Access-Controlled Inner Product Function-Revealing Encryption
Acharya, O., Feng, W., Langrehr, R., & O’Neill, A. (2025) · IACR Communications in Cryptology · doi:10.62056/abe0zo-3y · Cited by 1
Spatial Semantic-based Enhanced Address Parsing via Adaptive Weighted Learning
Qin, H., Wang, M., Li, Y., Zhang, J., & Zheng, Y. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761499 · Cited by 1
OFIA: An Object-centric Fine-grained Alignment Enhancement for Video-Text Retrieval
Huang, Z., Li, W., Dong, C., & Liu, M. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761041 · Cited by 1
Nguyen, M. H., Nguyen, T. T., Ta, M. N., Le, T., & Nguyen, H. T. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4960-3_9 · Cited by 1
“BERT has been successfully applied in various text ranking problems (Khattab and Zaharia 2020; Karpukhin et al. 2020), making it a practical and effective choice for encoding news titles within our recommendation framework.”
MR-SQL: Multi-level Retrieval Enhances Inference for LLM in Text-to-SQL
Wu, Z., Li, Z., Li, M., Zhang, J., He, Z., Yang, J., Zhao, Y., Fang, R., Li, Y., Li, Z., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-3830-0_27 · Cited by 6
A retrieval model with contextual correlation analysis for verbose queries
Podder, D., Paik, J. H., & Mitra, P. (2026) · Journal of Intelligent Information Systems · doi:10.1007/s10844-025-01009-4 · Cited by 1
Multi-Vector Biomedical Dense Retrieval with Knowledge-Enhanced Entity-Type Clustering
Deng, X., Tan, J., Zheng, X., & Dong, S. (2026) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3785368 · Cited by 1
A Comprehensive Study-Retrieval-Augmented Generation(RAG)
Kiruba, S., Anish, C. S., Krishna, R. S. B., & Rayen, S. J. (2025) · International Conference on Smart Structures and Systems (ICSSS) · doi:10.1109/icsss66939.2025.11346240 · Cited by 2
“Among other important models is ColBERT (Khattab & Zaharia, 2020), which used late interaction with contextualized embeddings to achieve fine-grained matching and high precision in passage ranking, but consumes a great memory and storage footprint due to the necessity of scoring at token-level.”
Code-Enhanced Cross-Perspective Bug Question Retrieval
Wang, M., Cai, Y., Xie, J., Wang, J., Wu, X., Liu, J., & Yang, R. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3789667 · Cited by 1
Min, Y., Sun, Y., Zhu, Y., Zhu, J., & Zhang, B. (2026) · Machine Intelligence Research · doi:10.1007/s11633-025-1591-z · Cited by 2
Improving Arabic Information Retrieval and Reranking Performance Using Knowledge Distillation
Hatem, M. A., Azouaou, F., & Batata, S. (2026) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3796229 · Cited by 3
“…mmarco-Arabic-mMiniLML-bi-encoder-KD-v1 Bi-encoder 0.184 0.777 Combined embedding (row 11+13) Bi-encoder 0.193 0.799 mColBERT [6] Late-interaction [15] 0.209 0.749 mMiniLM Cross-Encoder Reranker [6] Cross-encoder 0.219 - mT5 Cross-Encoder Reranker [6] Cross-encoder 0.235 - Cross-encoder and…”
InfluentialAugmenting Small Language Model for Better Medical Question Answering through Source Authentication
Das, S., Chatterji, S., & Mukherjee, I. (2026) · ACM Transactions on Information Systems · doi:10.1145/3797887 · Cited by 3
Legal Case Entailment via Optimal Transport–Enhanced Retrieval and Large Language Model Ranking
Tran, T. N., Nguyen, P. M., & Nguyen, M. L. (2026) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3789254 · Cited by 1
Multivector Reranking in the Era of Strong First-Stage Retrievers
Martinico, S., Nardini, F. M., Rulli, C., & Venturini, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21324-2_4 · Cited by 4
When Reducing Representations Improves Performance
Pasin, A., Faggioli, G., Ferro, N., Perego, R., & Tonellotto, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21289-4_30 · Cited by 1
Cross-Sensory Brain Passage Retrieval: Scaling Beyond Visual to Audio
McGuire, N., & Moshfeghi, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21289-4_31 · Cited by 1
“Addressing these limitations, McGuire and Moshfeghi [31] proposed Brain Passage Retrieval (BPR), which bypasses intermediate text generation by leveraging dense retrieval architectures [19,21] and contrastive learning to project EEG signals directly into passage representation spaces.”
InfluentialBeyond Correlations: A Downstream Evaluation Framework for Query Performance Prediction
Santra, P., Naskar, S. K., & Basuchowdhuri, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21300-6_43 · Cited by 2
Breaking Flat: A Generalised Query Performance Prediction Evaluation Framework
Santra, P., Naskar, S. K., & Basuchowdhuri, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21300-6_10 · Cited by 2
ALTER: a lightweight topic-aware representation legal case retrieval system
Wang, Z., & Yu, J. (2026) · Artificial Intelligence and Law · doi:10.1007/s10506-026-09519-4 · Cited by 1
brat : Aligned Multi-View Embeddings for Brain MRI Analysis
Kayser, M., Gridnev, M., Wang, W., Bain, M., Rangnekar, A., Chatterjee, A., Petrov, A., Veeraraghavan, H., & Swinburne, N. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00568 · Cited by 3
A COMPARATIVE STUDY OF CHUNKING STRATEGIES FOR RETRIEVAL-AUGMENTED GENERATION
Yuvzhenko, D., & Stirenko, S. (2026) · Kibernetyka ta Systemnyi Analiz · doi:10.34229/kca2522-9664.26.3.4 · Cited by 1
Musa, M. H., Salam, S., Norasikin, M. A., Hall, W., & Rusdi, J. F. (2026) · Discover Education · doi:10.1007/s44217-026-01580-0 · Cited by 1
Orchestrating Heterogeneous Experts: A Scalable MoE Framework with Anisotropy-Preserving Fusion
Liu, Y., Chen, W., Chen, X., & Li, M. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774905.3797243 · Cited by 1
A Comparative Performance Analysis: Vector Search vs Graph Databases for RAG Applications
Nandi, S. P., Venganti, V., Soni, V. R., & Nutalapati, V. (2026) · International Conference on Artificial Intelligence, Systems, and Emerging Technologies (ICAISET) · doi:10.1109/icaiset66439.2026.11541494 · Cited by 1
“More recent GraphRAG architectures combine vector similarity for initial candidate retrieval with graph traversal for contextual enrichment [8]; Microsoft's GraphRAG demonstrated significant gains on multi-hop queries through pre-materialized subgraph caching.”
Nikam, A., Palwe, S., Bartakke, S., Shinde, O., & Yadav, A. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.06.269 · Cited by 2
Lightweight Adapted Retrieval-Augmented Inference Network for Legal Issues
钱泓廷, Lin, J., Tang, J., Zhou, H., Peng, Y., Liu, L., & Liu, X. (2026) · Electronics · doi:10.3390/electronics15142996 · Cited by 1
“…exist to our BM25+ElasticSearch pipeline: dense retrieval (e.g., DPR [18]) improves paraphrase recall via vector mapping; late-interaction (e.g., ColBERT [19]) enables fine-grained similarity with offline indexing; sparse neural retrievers (e.g., SPLADE [20]) support semantic expansion.”
Multi-Vector Index Compression in Any Modality
Qin, H., Martin, A. A., Jha, R., Zuo, C., Kriz, R., & Durme, B. V. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809589 · Cited by 16
RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution
Nian, J., Li, F., Park, D. H., & Fang, Y. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809962 · Cited by 6
Han, J., Zhang, M., & Trajcevski, G. (2026) · Proceedings of the VLDB Endowment · doi:10.14778/3801059.3801067 · Cited by 1
Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing
Martinico, S., Nardini, F. M., Rulli, C., & Venturini, R. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809927 · Cited by 2
Metadata
- Authors
- Khattab, O., & Zaharia, M.
- Affiliations
- Stanford University (US)
- Venue
- Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
- Publisher
- ACM
- Published
- 2020-07-25
- Pages
- 39-48
- OpenAlex
- W3021397474
- Cited by
- 1,301
- References
- 21
- Citations by year
- 2026: 346 · 2025: 277 · 2024: 197 · 2023: 184 · 2022: 143 · 2021: 135 · 2020: 18
- FWCI
- 90.73
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (publishedVersion)
- Funders
- NSF (CNS-1651570)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- Colbert, BERT, document ranking, information retrieval, query-document similarity, efficient retrieval
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.