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 901–1,000 of 1,023
How Can Personalized Context Help? Exploring Joint Retrieval of Passage and Personalized Context
Wan, H., Li, H., Lu, S., Cui, X., & Danilevsky, M. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447921
“We conduct experiments using several popular pretrained modern neural retrieval systems including a late-interaction retrieval model ColBERT [8,20], single-vector retrieval models DPR [7], ANCE [30] and Sentence BERT (S-BERT) [17] with DistilBERT-TAS-B model [5,19].”
MethodInvestigating the Usage of Formulae in Mathematical Answer Retrieval
Reusch, A., Gonsior, J., Hartmann, C., & Lehner, W. (2024) · European Conference on Information Retrieval · doi:10.1007/978-3-031-56027-9_15 · Cited by 2
“Even though we only studied a model trained in a cross-encoder set up, the presented set up can also be used with ColBERT-based models [10] such as the one presented by Zhong et al. [33].”
MethodSelma: A Semantic Local Code Search Platform
Reusch, A., Lopes, G. C., Pertsch, W., Ueck, H., Gonsior, J., & Lehner, W. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56069-9_21
“We chose ColBERT [8] as our second retrieval method, because it combines the semantic modeling capacities of Transformer-Encoders with fast retrieval performance due to offline indexing.”
MethodKnowFIRES: A Knowledge-Graph Framework for Interpreting Retrieved Entities from Search
Arabzadeh, N., Golzadeh, K., Risi, C., Clarke, C. L. A., & Zhao, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56069-9_15
“For dense retrievers, we use SentenceBERT [28, 37] and ColBERT [20, 31], each offering unique approaches to estimating relevance.”
MethodDADR: A Denoising Approach for Dense Retrieval Model Training
Du, M., Li, S., Yu, J., Ma, J., Liu, H., Li, M., & Ji, B. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2387-4_11
Contextualization with SPLADE for High Recall Retrieval
Yang, E. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657919 · Cited by 1
“Dual-encoders fall into two categories: dense, such as DPR [13] and ColBERT [14], where text are encoded as one or more dense vectors, and learned-sparse retrievers (LSR) [26], such as EPIC [23] and SPLADE [8], where text are transformed into contextualized sparse vectors.”
Term Importance for Transformer-Based QA Retrieval: A Case Study of StackExchange
Tan, B. Z. Y., & Lauw, H. W. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589335.3651568
Bi-CAT: Improving Robustness of LLM-based Text Rankers to Conditional Distribution Shifts
Srinivasan, S., Sheng, S., Deshmukh, R., Luo, C., Dattatreya, Y., Sanyal, S., & Vishwanathan, S. V. N. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589335.3651947
“Several variants of this approach has been proposed by modifying the 𝜃 function [2, 7, 21] and loss function [1, 2, 6, 15, 17, 21].”
An Abstract-Level Patent Retrieval Model
Bai, Y., Chen, H., Lian, P., & Han, Y. (2023) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1145/3652628.3652710
“4)Late-interaction, such as ColBERT [16] and PreTTR [17], it is proved in experiments that the interaction of the first few layers in the hidden layer has a very limited effect on the final result, so only interact in the last layer, reducing calculate overhead.”
MethodToken Pruning by Dimensionality Reduction Methods on TCT-ColBERT for Reranking
Hina, N., Boughanem, M., & Dkaki, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-62700-2_7 · Cited by 1
On Backbones and Training Regimes for Dense Retrieval in African Languages
Oladipo, A., Adeyemi, M., & Lin, J. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657952
A Large-scale Offer Alignment Model for Partitioning Filtering and Matching Product Offers
Huang, W., Melo, A., & Pan, J. Z. (2024) · Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3626772.3661351
Enhancing Retrieval-Augmented LMs with a Two-Stage Consistency Learning Compressor
Xu, C., Zhao, D., Wang, B., & Xing, H. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5669-8_42 · Cited by 1
Multi-stage enhanced representation learning for document reranking based on query view
Liu, H., Zhu, X., Tang, Y. H., He, C., & Hao, T. (2024) · World Wide Web · doi:10.1007/s11280-024-01296-x
Hillebrand, L., Pradhan, P., Bauckhage, C., & Sifa, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70359-1_23
Retrieval and Sorting of Scientific Documents Based on Stacked Embedding and Hybrid Attention Model
Zeng, B., & Tian, X. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650167
Multi-DSI: Non-deterministic Identifier and Concept Alignment for Differentiable Search Index
Liu, Y. F., Jiang, J., & Cheng, P. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679971 · Cited by 1
Over-penalization for Extra Information in Neural IR Models
Usuha, K., Kato, M. P., & Fujita, S. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679975
Yang, W., Huo, T., & Liu, Z. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681307
“A lot of work aims to balance these two methods in terms of efficiency and performance [26, 31, 48, 54].”
CAGS: Context-Aware Document Ranking With Contrastive Graph Sampling
Huang, Z., Zhu, Y., Dou, Z., & Wen, J.-R. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3491996
“Recently, large-scale pre-trained language models (e.g., BERT [10] and BART [19]) were proposed and have been utilized for the context-aware document ranking task [20], [21], [22], [23].”
QuoteInspector: Gaining Insight about Social Media Discussions
Wu, P., Zhang, Y., Tan, W.-C., & Ives, Z. G. (2024) · Proceedings of the VLDB Endowment · doi:10.14778/3685800.3685910
DUNKS: Chunking and Summarizing Large and Heterogeneous Data for Dataset Search
Chen, Q., Zhou, X., Zhang, Z., & Cheng, G. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-77850-6_5 · Cited by 2
RePair My Queries: Personalized Query Reformulation via Conditional Transformers
Narayanan, Y. L., & Fani, H. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0579-8_16
“In a host of sparse and dense information retrieval methods including bm25 [25] and the recent colbert [12], and evaluation metrics such as mean average precision ( map ) and mean reciprocal rank ( mrr ), our experiments demonstrate that incorporating user when reformulating queries through…”
BackgroundMethodAlonso, O., & Baeza-Yates, R. (2024) · ACM eBooks · doi:10.1145/3674127.3674128
Searching Personal Collections
Bendersky, M., Metzler, D., Najork, M., & Wang, X. (2024) · ACM eBooks · doi:10.1145/3674127.3674142
Query-driven Search Functionality
Li, L. (2024) · ACM eBooks · doi:10.1145/3674127.3674133
Alonso, O., & Baeza-Yates, R. (2024) · ACM eBooks · doi:10.1145/3674127.3702962
Alonso, O., & Baeza-Yates, R. (2024) · ACM eBooks · doi:10.1145/3674127.3674129
Alonso, O., & Baeza-Yates, R. (2024) · ACM eBooks · doi:10.1145/3674127.3702961
Hersh, W., & Roberts, K. E. (2024) · ACM eBooks · doi:10.1145/3674127.3702960
Bast, H., Kalmbach, J., Klumpp, T., & Korzen, C. (2024) · ACM eBooks · doi:10.1145/3674127.3674134 · Cited by 1
Wang, Z., Huo, H., Xu, R., Yang, S., & Fang, T. (2024) · International Conference on Machine Learning and Natural Language Processing (MLNLP) · doi:10.1109/mlnlp63328.2024.10800230 · Cited by 1
Exploring Benefits of Bellwether Projects in Cross-Project IR-based Fault Localization
Amasaki, S., Leelaprute, P., Aman, H., & Yokogawa, T. (2024) · Euromicro Conference on Software Engineering and Advanced Applications (SEAA) · doi:10.1109/seaa64295.2024.00040
Text Retrieval in Restricted Domains by Pairwise Term Co-occurrence
Sneiders, E., & Henriksson, A. (2024) · Complex Systems Informatics and Modeling Quarterly · doi:10.7250/csimq.2024-41.05
Search Multiple Types of Research Assets From Jupyter Notebook
Li, N., Farshidi, S., & Zhao, Z. (2025) · Software Practice and Experience · doi:10.1002/spe.3406 · Cited by 2
Rectifying and Discriminating Hard Negatives for Biomedical Retrieval Question Answering
Bai, J., Li, Z., Zhao, B., Li, C., Lin, C., & Rong, W. (2025) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbbio.2025.3551290
“A prevalent choice for the ReQA solution is the utilization of the bi-encoders model [8], [9] instead of the cross-encoder model [10], [11] or late-interaction model [12], attributed to the former’s notable efficiency in scenarios involving a substantial number of answer candidates.”
Li, W., Li, Y., Shao, Y., & Bi, M. (2025) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3725733
“Rather than learning a single vector for the sentence, Colbert [Khattab and Zaharia 2020] takes a different approach that produces multiple vectors with PLM to catch token-level similarity, based on which a post-procedure calculates the similarity between sentences.”
MGS3: A Multi-Granularity Self-Supervised Code Search Framework
Li, R., Kang, J., Liu, Q., He, L., Zhang, Z., Sha, Y., Zhu, L., & Huang, Z. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709263 · Cited by 1
Graph Representation of Tables+Text and Compact Subgraph Retrieval for QA Tasks
Kumar, V., Sen, J., Chelani, B., & Chakrabarti, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88708-6_11 · Cited by 1
Semantically Proportioned nDCG for Explaining ColBERT’s Learning Process
Mueller, A., & Macdonald, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88708-6_22
“In recent years, dense retrieval approaches have achieved significant gains in retrieval effectiveness compared to traditional approaches [11,16,27], such as BM25 [20].”
InfluentialInvestigating the Performance of Dense Retrievers for Queries with Numerical Conditions
Fujimaki, H., & Kato, M. P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88714-7_19
An Optimized Content Retriever from Web Articles using Large Language Models and FAISS IndexingPreprint
Reddy, V., & Veeranjaneyulu, N. (2025) · Research Square · doi:10.21203/rs.3.rs-6411861/v1
MD2PR: A Multi-level Distillation based Dense Passage Retrieval ModelPreprint
Li, H., Hai, M., & Tang, D. (2025) · Research Square · doi:10.21203/rs.3.rs-6219315/v1
Barrett, J. S., Piccoli, B., Denaro, C. A., Schmidt, S., Vozmediano, V., Guzy, S., Barrett, K., Kwok, K., Russell, S., & Sibbald, D. (2025) · The Journal of Clinical Pharmacology · doi:10.1002/jcph.70028
“There is a vast variety of approaches to document ranking, such as DeepCT, ColBERT, 23 and RepBERT.”
User Interaction-Driven Refinement of Dense Retrieval Models
Goli, R. (2025) · Conference on Human Information Interaction and Retrieval · doi:10.1145/3698204.3716484
“Studies have shown that dense retrieval models consistently outperform sparse models, particularly in scenarios where queries and documents lack significant lexical overlap, thus providing more accurate and contextually relevant results [9].”
Using Computational Methods to Explore Law in Sermons
Totzeck, M. M., & Fuchs, V. (2025) · Laws · doi:10.3390/laws14030032
“In addition, approaches like ColBERT (Khattab and Zaharia 2020) allow for token-level embeddings, thereby preserving more granular details from the original text for evaluation.”
Liu, Z., Li, Y., Wang, J., & Cai, Y. (2025) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner64311.2025.00031
Ampomah, S. J., & Bandaluppi, S. S. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-94168-9_26
Few-Shot Multilingual Open-Domain QA from Five Examples
Jiang, F., Drummond, T. W., & Cohn, T. (2025) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00750 · Cited by 1
Liu, J., Symons, C. T., & Vatsavai, R. R. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8186-0_16
Tachioka, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-97144-0_7
A Comparative Analysis of Ai-Based Solutions for Clinical Documentation
Afonso, L. C., Almeida, J. R., & Oliveira, J. L. (2025) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms65348.2025.00026
Gosling Grows Up: Retrieval with Learned Dense and Sparse Representations Using Anserini
Lin, J., Chen, A. H., Lassance, C., Ma, X., Pradeep, R., Teofili, T., Xian, J., Yang, J.-H., Zhong, B., & Zhong, V. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730281 · Cited by 4
“Another family of successful models generates multiple vectors to represent each document; the most well known of these is ColBERT [25].”
The Second Tutorial on Retrieval-Enhanced Machine Learning: Synthesis and Opportunities
Díaz, F., Drozdov, A., Kim, T. E., Salemi, A., & Zamani, H. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3731695
μDS: Multi-Objective Data Snippet Extraction for Dataset Search
Zhou, X., Chen, Q., Chen, J., & Cheng, G. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730120 · Cited by 6
Yu, H. Q., & Siriwardhana, K. C. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-92517-7_12
A Survey on AI Search with Large Language ModelsPreprint
Li, J., Li, X., Zheng, Y. L., Jin, Y., Wang, S., Wu, J., Wang, Y., Wang, C., & Yuan, X. (2025) · Preprints.org · doi:10.20944/preprints202507.2024.v1 · Cited by 1
NeGLU: Negation-Aware Sparse Retrieval With Negative Weights for Product Search
An, G.-T., Park, J.-M. J., & Lee, K. S. (2025) · IEEE Access · doi:10.1109/access.2025.3596549
“Recent deep learning advances have driven the development of neural retrieval models such as Contextualized Late Interaction over BERT (ColBERT) [4] and LSR methods.”
A Survey on AI Search with Large Language ModelsPreprint
Li, J., Li, X., Zheng, Y. P., Jin, Y., Wang, S., Wu, J., Wang, Y., Wang, C., & Yuan, X. (2025) · Preprints.org · doi:10.20944/preprints202507.2024.v2 · Cited by 4
Curriculum-based adaptation of language model for knowledge graph: Handling low and noisy data
Duddukuri, Y. H., & Garapati, Y. (2024) · International Conference on Information Management & Machine Intelligence (ICIMMI) · doi:10.1145/3745812.3745892
Integration of Machine Learning and Large Language Models for Scalable Data Cleaning
Dawale, S., Kumawat, A., Mishra, L., Chitradevi, D., Saranya, K. R., & Pendela, A. (2025) · International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc65190.2025.11140947
SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval
Gu, W., Lyu, Z., Wang, Y., Zhang, H., Gao, C., & Lyu, M. R.-T. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3765748 · Cited by 3
Towards practical automatic document understanding
Ma, Y. (2025) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/201841
Global-Local Multi-Vector Fusion for Visual Text Retrieval
Bae, Y., & Bae, K. (2025) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2025.23.8.37
IndoColSmol: Lightweight Vision-Language Models for Multimodal Indonesian Document Search
Fritz, J. M., Utama, N. I., & Fa’rifah, R. Y. (2025) · International Conference on Data Science and Its Applications (ICoDSA) · doi:10.1109/icodsa67155.2025.11157156
A High-Speed FPGA Implementation for IVF-PQ Index Construction
Song, Y., Du, Y., & Wang, Z. (2025) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2025.3609631
“Google and other commercial search engines leverage machine learning models to embed web pages as vectors and retrieve relevant results via ANNS to achieve high queries per second (QPS) performance [1], [2], [3].”
Akl, A., & Hamdi, A. (2025) · Intelligent Methods, Systems, and Applications (IMSA) · doi:10.1109/imsa65733.2025.11167556 · Cited by 1
“Some early work on fusion includes multi-view learning [9], which aims to learn from different feature perspectives, and model combination in retrieval architectures like ColBERT [10], which employs late interaction to preserve fine-grained token-level alignment.”
Integrating RAG for Smarter Animal Certification Platforms
Montero, P. B., Gassen, J. B., Descovi, G., Barnasque, T. O., da Silva, G. R., Machado, F. R. H., Casanova, G. V., Maran, V., & Machado, A. K. (2025) · Information · doi:10.3390/info16100843
Rethinking Data Use in Large Language Models
Min, S., Hajishirzi, H., & Zettlemoyer, L. (2025) · Computational Linguistics · doi:10.1162/coli.a.573 · Cited by 1
Khan, A., Bukhari, S., Khattab, U., & Kamal, A. (2025) · VFAST Transactions on Software Engineering · doi:10.21015/vtse.v13i3.2137
Nguyen, C. M., Tran, H. A. P., Thai, P. K., Nguyen, H. D., & Nguyen, V. T. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06069-3_10
On the Theoretical Advantages of Bilinear Similarities in Dense Retrieval
Chatterjee, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06069-3_11
Retrieval-Augmented Vision–Language Agents for Child-Centered Encyclopedia Learning
Du, J., Liu, W., Ye, J., Zhou, D., & Liu, F. (2025) · Applied Sciences · doi:10.3390/app151910821
Improving Information Retrieval in Turkish: A ColBERT-Based Approach
Saoud, A., Kazerooni, P., Amasyalı, M. F., & Kesgin, H. T. (2025) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-031-88999-8_7
From Trigrams to Transformers and AI: Semantic and Multilingual Search
Baťalík, P., Marcinco, M., Turňa, J., Dubec, J., & Lang, J. (2025) · International Conference on Intelligent Mechanical and Human-Computer Interaction Technology (IHCIT) · doi:10.1109/ihcit66787.2025.11198952
“Similarly, the ColBERT ranking model [7] addresses BERT’s runtime inefficiency by separately encoding queries and documents, then performing a lightweight interaction that allows pre-computation of document embeddings.”
Diversification and Fairness in Search: Two Sides of the Same Coin?
Cherumanal, S. P., Scholer, F., & Spina, D. (2025) · ACM Transactions on Information Systems · doi:10.1145/3774320 · Cited by 1
Zhou, W., Song, C., Jiao, S.-S., & Luo, X.-F. (2025) · IEEE International Conference on Software Quality, Reliability and Security Companion · doi:10.1109/qrs-c65679.2025.00055
“Techniques such as TF-IDF and mutual information are often employed to assess and filter words based on their significance, such as ColBERT[23], R 3 [24], and RocketQA[25].”
Optimizing Diagnostic Accuracy in Healthcare by Using Deep Learning
Sinhal, A., Sahu, N., & Sinhal, A. (2025) · IEEE World Conference on Applied Intelligence and Computing (AIC) · doi:10.1109/aic66080.2025.11211920
Xu, Z., Chen, Z., Xu, J., Tan, L., & Shardt, Y. A. W. (2025) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon58223.2025.11221863
FuseRank: Filtered Vector Search in Multimodal Structured Data
Paraschakis, D., Ros, R., Asaad, A., Borg, M., & Runeson, P. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.495
Urban In-context Learning: A New Paradigm for Urban Indicator Prediction
Deng, Z., Han, L., Zhu, T., Miao, Z., Xu, Y., & Sun, L. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761426 · Cited by 1
“ColBERT is an effective passage search method that considers the token-level similarity within documents.”
InfluentialDense Retrieval for Aggregated Search
Mei, L., Liu, S., Zhao, Z., Yan, Q., Mao, J., & Wen, J.-R. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761197
A Needle in a Haystack: Finding Contextual Knowledge for Video Question Answering
Ichimiya, S., & Nakashima, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4398-4_25
An Empirical Evaluation of Deep Learning Techniques for Clinical Video Retrieval
Liu, Z., Becevic, M., Braddock, A. S., Popescu, M., Simões, E. J., & Rao, P. R. (2025) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr67560.2025.00013
Fixed-Point Splitting Quantization: Improving Accuracy for Compute-in-Memory Vector Retrieval
You, S., Gao, S., Xu, Q., Li, X., & Chen, W. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4094-5_20
Generating Cost Optimized Smart Contracts from Deep Learning Code using Large Language Models
Nikumbh, S. S., Chakraborty, S., & Sural, S. (2025) · International Conference on Blockchain Computing and Applications (BCCA) · doi:10.1109/bcca66705.2025.11229467
How Can Disparate Retrieval Methods Work Together Effectively?
Tank, S. (2025) · American journal of student research. · doi:10.70251/hyjr2348.36588593
Embedding-Based Sparse Retrieval in E-Commerce Search
Wang, L., He, J., Xu, S., Lin, Y., Cheng, Y., Yin, W., Wang, D., & Feng, T. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4367-0_27
Transformer Based Argumentation Mining in English Language: BERT for Encoding and T5 for Decoding
Singh, R. B., Sinha, S., & Singh, A. (2025) · Journal of Emerging Technologies and Innovative Research · doi:10.56975/jetir.v12i11.572270
Late-Interaction InfoNCE: A Novel Contrastive Loss Function with Combined Similarity Metrics
Bu, Y., Wang, L., Huang, T. C., Hamdulla, A., Zhang, H., & Zhang, Q. (2025) · International Symposium on Computer and Information Processing Technology (ISCIPT) · doi:10.1109/iscipt67144.2025.11264929
“For instance, ColBERT [23]’s token-level interactions remain constrained by static pre-fusion representations.”
A Study of Multilingual Approaches to Vietnamese Information Retrieval
Nguyen, N. T. B., Hải, N. T., Hieu, N. T., & Tien, N. T. (2025) · International Conference on Advanced Technologies for Communications · doi:10.1109/atc67618.2025.11268667
Unified Cognitive Consciousness Theory: Formalization, Validation, and Outlook
Chang, E. Y. (2025) · ACM eBooks · doi:10.1145/3749421.3749438
“…al. 2020] and pre-training with retrieval methods such as REALM (Retrieval-Augmented Language Model) and Retrieval-Enhanced Transformer (RETRO) [Guu et al. 2020, Borgeaud et al. 2022], both enabled by dense retrievers and late-interaction rankers [Karpukhin et al. 2020, Khattab and Zaharia 2020].”
Intelligent Retrieval of Engineering Material Price Based on Dual-Channel Hybrid Semantic Modeling
Yang, C., Li, F., Pei, H., Tu, C., Zhang, H., & Zhao, X. (2025) · International Conference on Internet of Things and Cloud Computing Technology (IoTCCT) · doi:10.1145/3776865.3776921
Al-Saadi, A. J. M., Alsadi, A. M., Hasan, M. A., Darb, Q. S., AlHommada, M. R., Jalial, S. A., & Ibrahim, H. A. (2025) · International Conference on Cyber Resilience (ICCR) · doi:10.1109/iccr67387.2025.11291889
Retrieval and Ranking Model of Scientific Literature Based on MiniLM-Formula and AHP
Yang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9849-3_7
Semantic Caching for Mitigating LLM Inference Latency in Real-Time Query Understanding
Alam, P. K. (2025) · European Modern Studies Journal · doi:10.59573/emsj.9(5).2025.12
MAMR: Modality-Aligned Multi-modal Retrieval
Xu, Y., Mo, J., Lin, F., Chen, Z., Chen, C., & Liu, S. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228736
SIGIR-AP 2025 Tutorial on Retrieval and Ranking with LLMs (R 2 LLMs)
Zuccon, G., Zhuang, S., Ma, X., & Koopman, B. (2025) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3767695.3769522 · Cited by 1
Evaluating BERT Models for Semantic Retrieval in Long Portuguese Legal Documents
Justino, A. F., Junior, A. F. L. J., Marcacini, R. M., & Lobato, F. M. F. (2025) · doi:10.5753/eniac.2025.14328
“Alternativamente, a abordagem de “interac¸˜ao tardia” [Khattab and Zaharia 2020] calcula a relevˆancia de forma mais granular, a n´ıvel de to-ken .”
ToolSEE: Agent Tool Search Engine for Efficient and Scalable Tool Discovery Using RetrievalPreprint
Vadlapati, P. (2025) · Preprints.org · doi:10.20944/preprints202512.1744.v1
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.