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 401–500 of 1,023
Knowledge-Augmented Zero-Shot Method for Power Equipment Defect Grading with Chain-of-Thought LLMs
Du, J., Li, B., Chen, Z., Shen, L., Liu, P., & Ran, Z. (2025) · Electronics · doi:10.3390/electronics14153101 · Cited by 7
Leveraging RAG with ACP & MCP for Adaptive Intelligent Tutoring
Modran, H. A. (2025) · Applied Sciences · doi:10.3390/app152111443 · Cited by 8
Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking
Ji, Y., Xu, Z., Liu, Z., Yan, Y., Yu, S., Li, Y., Liu, Z., Gu, Y., Yu, G., & Sun, M. (2025) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3767695.3769491 · Cited by 20
“Nevertheless, only relying on one embedding usually shows less effectiveness in representing documents from different views that can match queries [23, 54].”
A Pre-training Strategy for Zero-Resource Response Selection in Knowledge-Grounded Conversations
Tao, C., Chen, C., Feng, J., Wen, J.-R., & Yan, R. (2021) · doi:10.18653/v1/2021.acl-long.343 · Cited by 8
“Fortunately, the ad-hoc retrieval task (Harman, 2005; Khattab and Zaharia, 2020) in the information retrieval area provides a potential solution to simulate the process of knowledge seeking.”
BackgroundTADI: Topic-aware Attention and Powerful Dual-encoder Interaction for Recall in News Recommendation
Jiang, J. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.1047 · Cited by 7
“The evaluation metrics in our experiments are used on both news ranking models and recall models, such as previous works (Wang et al., 2023; Khattab and Zaharia, 2020; Cen et al., 2020).”
BackgroundMethodRevisiting Bag of Words Document Representations for Efficient Ranking with Transformers
Rau, D., Dehghani, M., & Kamps, J. (2024) · ACM Transactions on Information Systems · doi:10.1145/3640460 · Cited by 12
Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrieval
Jin, N., Li, D., Chen, J., Siebert, J. I., & Chen, Q. (2023) · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL) · doi:10.18653/v1/2023.ijcnlp-short.18 · Cited by 12
SC-Net: Multimodal metaphor detection using semantic conflicts
He, X., Yu, L., Tian, S.-W., Yang, Q.-M., & Long, J. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127825 · Cited by 7
ConvSDG: Session Data Generation for Conversational Search
Mo, F., Yi, B., Mao, K., Qu, C., Huang, K., & Nie, J. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589335.3651940 · Cited by 10
ESPN: Memory-Efficient Multi-vector Information Retrieval
Shrestha, S., Reddy, N., & Li, Z. (2024) · ACM SIGPLAN International Symposium on Memory Management (ISMM) · doi:10.1145/3652024.3665515 · Cited by 19
“Advancing this paradigm, late interaction models like ColBERT encode documents at the granularity of tokens, resulting in multi-vector representations (Khattab & Zaharia, 2020).”
BackgroundMethodResultNegative Sampling Techniques for Dense Passage Retrieval in a Multilingual Setting
Rajapakse, T. C., Yates, A., & de Rijke, M. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657854 · Cited by 8
“The external models available in the multilingual retrieval setting tend to be less effective and reliable compared to the models available for English such as ColBERT [9].”
Pipeline and dataset generation for automated fact-checking in almost any language
Drchal, J., Ullrich, H., Mlynář, T., & Moravec, V. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10113-5 · Cited by 12
“Our previous research has shown ColBERT [24] to work well for the retrieval task in less-resourced languages [6].”
Gandalf: Learning Label-label Correlations in Extreme Multi-label Classification via Label Features
Kharbanda, S., Gupta, D., Schultheis, E., Banerjee, A., Hsieh, C., & Babbar, R. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3672063 · Cited by 9
Self Data Augmentation for Open Domain Question Answering
Zhang, Q., Zheng, M., Chen, S., Liu, H., & Fang, M. (2025) · ACM Transactions on Information Systems · doi:10.1145/3707449 · Cited by 9
“In conclusion, most existing methods aim to construct large and strong models of retrieval through pre-training architecture [17, 18, 20, 58, 59] or complicated training progress [28, 29, 46], which are complex and costly.”
Decoy Effect in Search Interaction: Understanding User Behavior and Measuring System Vulnerability
Chen, N., Liu, J., Fang, H., Luo, Y., Sakai, T., & Wu, X.-M. (2025) · ACM Transactions on Information Systems · doi:10.1145/3708884 · Cited by 16
Zhang, Y., Huang, B., Yuan, W., Jiang, Z., Peng, L., Chen, S., & Tan‐Soo, J. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104090 · Cited by 8
On the Robustness of Generative Information Retrieval Models: An Out-of-Distribution Perspective
Liu, Y.-A., Zhang, R., Guo, J., Zhou, C., de Rijke, M., & Cheng, X. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88711-6_26 · Cited by 15
Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval
Pang, M., Yuan, C., He, X., Fang, Z., Xie, D., Qu, F., Jiang, X. L., Peng, C., Lin, Z., Luo, Z., et al. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3701716.3715228 · Cited by 33
“The introduction of pre-trained language models, particularly BERT [8], has revolutionized information retrieval, paving the way for dense retrieval meth-ods such as Dense Passage Retrieval (DPR) [7], ColBERT [9], and GTR [13].”
When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions
Huang, Z., Wu, A., Shen, Y., Cheng, G., & Qu, Y. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.84 · Cited by 8
SDR: Efficient Neural Re-ranking using Succinct Document Representation
Cohen, N., Portnoy, A., Fetahu, B., & Ingber, A. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.457 · Cited by 20
TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval
Leszczynski, M., Fu, D. Y., Chen, M. F., & Ré, C. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.169 · Cited by 13
MatchACNN: A Multi-Granularity Deep Matching Model
Chang, G., Wang, W., & Hu, S. (2022) · Neural Processing Letters · doi:10.1007/s11063-022-11047-6 · Cited by 7
Early Stage Sparse Retrieval with Entity Linking
Shehata, D., Arabzadeh, N., & Clarke, C. L. A. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557588 · Cited by 7
“mance improvement by mapping queries and documents to dense low-dimensional embedding-based contextualized representations to softly match query-document pairs beyond the explicit text surface form [19, 24].”
BackgroundKharbanda, S., Banerjee, A., Gupta, D., Palrecha, A., & Babbar, R. (2021) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3539618.3591699 · Cited by 14
IR From Bag-of-words to BERT and Beyond through Practical Experiments
Macdonald, C., Tonellotto, N., & MacAvaney, S. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482028 · Cited by 7
“ACM ISBN 978-1-4503-8446-9/21/11. . . $15.00 https://doi.org/10.1145/3459637.3482028 efforts to replace the traditional inverted index with an embeddingbased index (e.g., ANCE [16], ColBERT [6], and ColBERT-PRF [15]).”
InfluentialGLOW : Global Weighted Self-Attention Network for Web Search
Shan, X., Liu, C., Xia, Y., Chen, Q., Zhang, Y., Ding, K., Liang, Y., Luo, A., & Luo, Y. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671546 · Cited by 11
Sen, P., Saha, S., Ganguly, D., Verma, M., & Roy, D. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557637 · Cited by 7
Dense Retrieval with Entity Views
Tran, H. D., & Yates, A. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557285 · Cited by 11
“To fix this issue, a representation compression technique is implemented to cut down space requirement in ColBERTv2 [37].”
BackgroundMethodDo Lessons from Metric Learning Generalize to Image-Caption Retrieval?
Bleeker, M., & de Rijke, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-99736-6_36 · Cited by 7
Query expansion with artificially generated textsPreprint
Claveau, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.08787 · Cited by 7
Wang, Z., Wu, D., Nguyen, Q., & Wang, K. (2026) · Medicine Bulletin · doi:10.1002/mdb2.70033 · Cited by 6
Chen, Q., Luo, W., Huang, Z., Lin, T., Wang, X., Soylu, A., Ell, B., Zhou, B., Kharlamov, E., & Cheng, G. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657866 · Cited by 10
Coherence-based Query Performance Measures for Dense Retrieval
Vlachou, M., & Macdonald, C. (2024) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3664190.3672518 · Cited by 10
“More recently, pre-trained language models (PLMs) have introduced neural network architectures that encode the embeddings of queries and documents [15, 27, 28, 56], and have led to increased retrieval effectiveness.”
Clavié, B., Cooper, N., & Warner, B. C. (2025) · Natural Language Processing Journal · doi:10.1016/j.nlp.2025.100150 · Cited by 14
Constructing and Evaluating Declarative RAG Pipelines in PyTerrier
Macdonald, C., Fang, J., Parry, A., & Meng, Z. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730150 · Cited by 12
“For example, it does not supportmulti-vectordense retrieval modelssuchas ColBERT[21] or learned sparse retrieval models such as SPLADE [11], which are two families of strong retrieval models from the literature.”
Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval
Most, A., Winjum, J., Bhattarai, M., Jones, S. M., Ranasinghe, N. R., Biswas, A., & O’Malley, D. (2025) · ACM Symposium on Document Engineering (DocEng) · doi:10.1145/3704268.3742698 · Cited by 18
PyLate: Flexible Training and Retrieval for Late Interaction Models
Chaffin, A., & Sourty, R. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761608 · Cited by 34
CEQE to SQET: A study of contextualized embeddings for query expansion
Naseri, S., Dalton, J., Yates, A., & Allan, J. (2022) · Information Retrieval · doi:10.1007/s10791-022-09405-y · Cited by 10
“Recent research (Gao et al., 2020; Khattab & Zaharia, 2020; MacAvaney et al., 2020; Zhan et al., 2020; Xiong et al., 2021) uses Transformer models to produce query and document representations that can be used for (relatively) efficient first-stage retrieval.”
MethodZero-shot Query Reformulation for Conversational Search
Yang, D., Zhang, Y., & Fang, H. (2023) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3578337.3605143 · Cited by 6
“The reason we choose TCTColBERT over ColBERT [7] is due to the latter’s prohibitive memory usage.”
BackgroundMethodLim, Q. Z., Lee, C. P., Lim, K. M., & Samingan, A. K. (2024) · IEEE Access · doi:10.1109/access.2024.3403101 · Cited by 8
“The first method involves encoding queries and documents using distinct encoders, followed by computing the similarity between the encoded representations [42], [43], [44].”
MethodEarly Exit Strategies for Approximate k -NN Search in Dense Retrieval
Busolin, F., Lucchese, C., Nardini, F. M., Orlando, S., Perego, R., & Trani, S. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679903 · Cited by 11
ir_explain: A Python Library of Explainable IR Methods
Saha, S., Agarwal, H., Venktesh, V., Anand, A., Mohanty, S., Majumdar, D., & Mitra, M. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730343 · Cited by 8
“The experiments were conducted on the same set of IR models (DCT [10], QE BERT [21], ANCE [45], CBERT [16], MonoT5 [29]) as in [21].”
Constructing Set-Compositional and Negated Representations for First-Stage Ranking
Krasakis, A. M., Yates, A., & Kanoulas, E. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761238 · Cited by 7
BOSS: Bandwidth-Optimized Search Accelerator for Storage-Class Memory
Heo, J., Lee, S.-Y., Min, S., Park, Y., Jung, S. J., Ham, T. J., & Lee, J. W. (2021) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca52012.2021.00030 · Cited by 6
“The top-k list is just a tiny fraction of the entire inverted index in the pooled memory. k is usually small since most users browse only the first few pages of search results [27], [38], [48].”
BackgroundLi, R., Wang, L., Jiang, Z., Hu, Z., Zhao, M., & Lu, X. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07072-0 · Cited by 7
“Additionally, MIPS between multi-vectors of the query and documents is also employed for fine-granular retrieval scoring [25].”
BackgroundMethodLoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback
Zhu, Y., Pang, L., Lan, Y., Shen, H., & Cheng, X. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3532017 · Cited by 6
Multi-views contrastive learning for dense text retrieval
Yu, Y., Zeng, J., Zhong, L., Gao, M., Wen, J., & Wu, Y. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110624 · Cited by 7
Balancing Lexical and Semantic Quality in Abstractive Summarization
Sul, J., & Choi, Y. S. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-short.56 · Cited by 10
Clarifying Questions in Math Information Retrieval
Mansouri, B., & Jahedibashiz, Z. (2023) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3578337.3605123 · Cited by 6
WebUltron: An Ultimate Retriever on Webpages Under the Model-Centric Paradigm
Zhou, Y., Yao, J., Wu, L., Dou, Z., & Wen, J.-R. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3332858 · Cited by 9
“Recognizing that retrieval performance can be constrained by the dot product of individual vectors, a line of research introduces lightweight interaction layers to capture more fine-grained matching relationships, such as the multi-vector encoding model [32] and ColBERT [33].”
Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories
Ge, S., Xiong, C., Rosset, C., Overwijk, A., Han, J., & Bennett, P. N. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.111 · Cited by 14
An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models
Liu, Q., Guo, G., Mao, J., Dou, Z., Wen, J.-R., Jiang, H., Zhang, X., & Cao, Z. (2024) · ACM Transactions on Information Systems · doi:10.1145/3639818 · Cited by 19
“Combining the advantages of cross-encoders and bi-encoders, Khattab and Zaharia [23] proposed a soft late-interaction model named ColBERT, and Gao et al. [17] proposed a hard late-interaction model named COIL.”
BackgroundMethodInfluentialLearning to Jointly Transform and Rank Difficult Queries
Bigdeli, A., Arabzadeh, N., & Bagheri, E. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56066-8_5 · Cited by 11
“As such, we first report the performance of our proposed fused approach [7] compared to the performance of the various state-of-the-art neural baselines [21,13,29] over all queries in Table 1.”
ResultA simple and efficient dialogue generation model incorporating commonsense knowledge
Son, G., & Kim, M. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123584 · Cited by 6
Manotumruksa, J., Dalton, J., Meij, E., & Yılmaz, E. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3512074 · Cited by 6
CODEC: Complex Document and Entity Collection
Mackie, I., Owoicho, P., Gemmell, C., Fischer, S., MacAvaney, S., & Dalton, J. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531712 · Cited by 17
“The document corpus pipeline takes the focused seed websites and uses Common Crawl and URL pattern matching to extract 300GB of HTML across recent crawls in 2021 (CC-MAIN-2021-[21,17,10,14]).”
BackgroundMethodTopic-Grained Text Representation-Based Model for Document Retrieval
Du, M., Li, S., Yu, J., Ma, J., Ji, B., Liu, H., Lin, W., & Yi, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-15934-3_64 · Cited by 6
MS-Shift: An Analysis of MS MARCO Distribution Shifts on Neural Retrieval
Lupart, S., Formal, T., & Clinchant, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-28244-7_40 · Cited by 21
“…domains and tasks, Thakur et al. show how cross-encoders, as well as retrieval models with lexical priors such as doc2queryT5 [32] or ColBERT [24], tend to be more robust, while dense bi-encoders such as DPR [23] or TAS-B [20] seem to suffer more from domain shifts – with performance lower…”
CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion
He, X., Gong, Y., Jin, A.-L., Zhang, H., Dong, A., Jiao, J., Yiu, S., & Duan, N. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.651 · Cited by 10
CFE2: Counterfactual Editing for Search Result Explanation
Xu, Z., Lamba, H., Ai, Q., Tetreault, J., & Jaimes, A. (2024) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3664190.3672508 · Cited by 18
Open-domain conversational search assistants: the Transformer is all you need
Ferreira, R., Leite, M., Semedo, D., & Magalhães, J. (2022) · Information Retrieval · doi:10.1007/s10791-022-09403-0 · Cited by 9
“Alternatively, there are approaches that separately encode the query and the passage, such as bi-encoders (Dinan et al. 2019; Mazaré et al. 2018; Khattab and Zaharia 2020) and poly-encoders (Humeau et al.”
Method(2022) · doi:10.1145/3477495.3531658 · Cited by 6
Pruning the Index Contents for Memory Efficient Open-Domain QAPreprint
Fajčík, M., Dočekal, M., Ondrej, K., & Smrž, P. (2021) · arXiv (Cornell University) · doi:10.13140/rg.2.2.32959.02727 · Cited by 9
Gao, M., Lu, P., Zhao, Z., Bi, X., & Wang, F. (2024) · International Conference on Machine Learning and Computer Application (ICMLCA) · doi:10.1109/icmlca63499.2024.10753879 · Cited by 10
“Khattab and Zaharia [10] developed ColBERT, a late interaction model that improved retrieval but required significant amounts of training data.”
IGP: Efficient Multi-Vector Retrieval via Proximity Graph Index
Bian, Z., Yiu, M. L., & Tang, B. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730004 · Cited by 21
A Learnable Fully Interacted Two-Tower Model for Pre-Ranking System
Xiong, C., Yu, X., Xu, W., Cheng, L., Yuan, C., & Mo, L. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3729881 · Cited by 5
“Therefore, the overall time complexity of the pre-ranking two-tower model is 𝑂 ( 𝑁 + 𝑘𝑀 ) , where 𝑁 is the time taken for a neural network model inference and 𝑀 is the time consumed for item retrieval and scoring between each user-item representation pair.”
Multi-level vision language interaction learning for cross-modal retrieval
Wang, H., Liu, F., Jiao, L., Wang, J., Li, S., Li, L., Chen, P., Liu, X., & Ma, W. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103481 · Cited by 13
Demographically-Inspired Query Variants Using an LLM
Alaofi, M., Ferro, N., Thomas, P., Scholer, F., & Sanderson, M. (2025) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3731120.3744608 · Cited by 9
Peng, X., Jiang, H., Chen, J., Liu, M., & Chen, X. (2025) · Scientific Reports · doi:10.1038/s41598-025-31102-1 · Cited by 9
Long, Q., Chen, H., Zhao, C., Du, X., Wang, X., Wang, P., Li, C., Zhou, Y., & Zhu, H. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818479 · Cited by 11
CoSBERT: A Cosine-Based Siamese BERT-Networks Using for Semantic Textual Similarity
Yu, W., Weng, Y., Lin, R., & Tang, Y. Z. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-2356-4_30 · Cited by 6
Learning Query-aware Embedding Index for Improving E-commerce Dense Retrieval
Li, M., Yuan, C., Wang, B., Zhuo, J., Wang, S., Liu, L., & Xu, S. (2023) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3539618.3591834 · Cited by 11
“Our method is a general framework, which could be adapted in various versions of two-tower (e.g, MGDSPR [15], Colbert [14]), and different product quantization.”
BackgroundTrapp, S., Großer, N., & Warschat, J. (2023) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-42532-5_2 · Cited by 6
Retrieval-Augmented Knowledge-Intensive Dialogue
Wang, Z., Gong, P., Zhang, Y., Gu, J., & Yang, X. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44693-1_2 · Cited by 8
Investigating the Effects of Sparse Attention on Cross-Encoders
Schlatt, F., Fröbe, M., & Hagen, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56027-9_11 · Cited by 11
“One strategy for using PLMs in ranking is to separate the encoding of queries and documents (or passages) [23, 24, 37, 41].”
BackgroundMethodRevisiting Document Expansion and Filtering for Effective First-Stage Retrieval
Mansour, W. A., Zhuang, S., Zuccon, G., & Mackenzie, J. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657850 · Cited by 11
“In particular, embedding-based retrieval techniques and neural re-ranking strategies have been shown to capture similarity beyond simple term matching systems, resulting in improvements in various search contexts [24, 30, 33, 57].”
BackgroundRetrieval-Enhanced Machine Learning: Synthesis and Opportunities
Díaz, F., Drozdov, A., Kim, T. E., Salemi, A., & Zamani, H. (2024) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3673791.3698439 · Cited by 7
Evaluating Relative Retrieval Effectiveness with Normalized Residual Gain
Bigdeli, A., Arabzadeh, N., Bagheri, E., & Clarke, C. L. A. (2024) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3673791.3698410 · Cited by 8
LLM-based IR-system for bank supervisors
Aarab, I. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112914 · Cited by 5
“Novel IR frameworks, such as ColBERT by Khattab and Zaharia (2020), leverage a late BERT-based interaction for e ffi cient passage search, balancing between e ff ectiveness and cost-e ffi ciency.”
Retrieval with Learned Similarities
Ding, B., & Zhai, J. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714822 · Cited by 10
“Their most basic versions preserve some dot product-related structures, but turn either the query or the item into multiple embeddings, and rely on a max operator to combine those similarity values [Li et al., 2019, Khattab and Zaharia, 2020].”
D'Erasmo, G., Trappolini, G., Silvestri, F., & Tonellotto, N. (2025) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3731120.3744579 · Cited by 7
“Dense retrieval models [10, 16, 17] are widely studied in Information Retrieval (IR) because they embed queries and documents into a latent space with many dimensions, where vector similarities capture nuanced semantic relationships [19, 21].”
Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generation
Li, S., & Ramakrishnan, N. (2025) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3731120.3744590 · Cited by 13
“Its strong performance across datasets highlights its robustness and adaptability, making it a promising so-lution for open-domain QA tasks that require flexibility in handling diverse knowledge sources and query structures.”
Li, Y., Zhang, H., Zhang, Y., Cai, H., Cai, M., Wang, S., Xiong, H., Kong, L., Yin, D., & Chen, L. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737258 · Cited by 9
“Concretely, Transformer-based rankers [12, 45] and BERT-based rankers [15, 23] are employed to perform ranking tasks with multiple losses.”
M 2 oERank: Multi-Objective Mixture-of-Experts Enhanced Ranking for Satisfaction-Oriented Web Search
Li, Y., Zhang, H., Zhang, Y., Ma, X., Ye, W., Song, N., Wang, S., Xiong, H., Yin, D., & Chen, L. (2025) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65448.2025.00333 · Cited by 5
“Recent studies have shown that hybrid approaches—combining sparse retrieval (term matching) with dense embeddings from PLMs—better capture semantic nuances across various content types [4], [5], [15].”
An in-depth study on adversarial learning-to-rank
Yu, H.-T., Piryani, R., Jatowt, A., Inagaki, R., Joho, H., & Kim, K.-S. (2023) · Information Retrieval · doi:10.1007/s10791-023-09419-0 · Cited by 9
“To reconcile efficiency and contextualization, ColBERT (Khattab & Zaharia, 2020) was proposed by introducing a late interaction architecture that independently encodes the query and the document.”
MethodColBERT-FairPRF: Towards Fair Pseudo-Relevance Feedback in Dense Retrieval
Jaenich, T., McDonald, G., & Ounis, I. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-28238-6_36 · Cited by 5
“Baselines: We compare our proposed ColBERT-FairPRF approach against the ColBERT [9] and ColBERT-PRF [15] approaches.”
COILcr: Efficient Semantic Matching in Contextualized Exact Match Retrieval
Fan, Z., Gao, L., Jha, R., & Callan, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-28244-7_19 · Cited by 8
“To tackle this problem, researchers explored using contex-tualized representations in lexical retrieval [29,15,22] under soft match settings.”
BackgroundEfficient Text-to-Code Retrieval with Cascaded Fast and Slow Transformer Models
Gotmare, A. D., Li, J., Joty, S., & Hoi, S. C. H. (2023) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3611643.3616369 · Cited by 8
A Multi-Granularity-Aware Aspect Learning Model for Multi-Aspect Dense Retrieval
Sun, X., Bi, K., Guo, J., Yang, S., Zhang, Q., Liu, Z., Zhang, G., & Cheng, X. (2024) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3616855.3635770 · Cited by 10
Multiscale Matching Driven by Cross-Modal Similarity Consistency for Audio-Text Retrieval
Wang, Q., Gu, J.-C., & Ling, Z.-H. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446302 · Cited by 8
“As depicted in Figure 1, drawing inspiration from the SCAN model [10] and the late interaction concept introduced by COLBERT [24], the computation of cross-modal similarity adopts a multiscale framework, progressing from local to global levels.”
MethodDREQ: Document Re-ranking Using Entity-Based Query Understanding
Chatterjee, S., Mackie, I., & Dalton, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56027-9_13 · Cited by 8
Enhancing Dataset Search with Compact Data Snippets
Chen, Q., Chen, J., Zhou, X., & Cheng, G. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657837 · Cited by 11
“DR 2 ( ft ) is a fine-tuned dense reranker based on ColBERT [24] fed with subgraphs extracted from RDF data.”
Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks
Zhuang, S., Khramtsova, E., Ma, X., Koopman, B., Lin, J., & Zuccon, G. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730056 · Cited by 7
“We conduct the attack experiments on two popular document screenshot retrievers: DSE [19], 1 a single-embedding bi-encoder model, and ColPali [7], 2 a ColBERT-like [11] multi-vector embedding dense retriever.”
Chia, Y. K., Witteveen, S., & Andrews, M. (2020) · doi:10.18653/v1/2020.textgraphs-1.14 · Cited by 6
Adaptive Batch Scheduling for Open-Domain Question Answering
Choi, D., Shin, M., Kim, E., & Shin, D. R. (2021) · IEEE Access · doi:10.1109/access.2021.3103963 · Cited by 7
Multilingual Semantic Sourcing using Product Images for Cross-lingual Alignment
Mangrulkar, S., Ankith, M. S., & Sembium, V. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3487553.3524204 · Cited by 6
Scientific Documents Retrieval Based on Graph Convolutional Network and Hesitant Fuzzy Set
Li, X., Tian, B., & Tian, X. (2023) · IEEE Access · doi:10.1109/access.2023.3259234 · Cited by 5
“Also, there are many retrieval methods based on neural network meth-ods, Dense Passage Retrieval (DPR) [12], kernel-based neural model for document ranking (K-NRM) [13], etc. ColBERT [14] introduces a late interaction system to obtain fine-grained similarity for queries and documents.”
MethodBaumgärtner, T., Ribeiro, L. F. R., Reimers, N., & Gurevych, I. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.614 · Cited by 11
Pre-training with Aspect-Content Text Mutual Prediction for Multi-Aspect Dense Retrieval
Sun, X., Bi, K., Guo, J., Ma, X., Fan, Y., Shan, H., Zhang, Q., & Liu, Z. (2023) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3583780.3615157 · Cited by 9
Explainability of Text Processing and Retrieval Methods: A Survey
Saha, S., Majumdar, D., & Mitra, M. (2026) · ACM Computing Surveys · doi:10.1145/3801957 · Cited by 10
“They concluded that passage ranking for MSMARCO is more related to a question answering (QA) task, and therefore, better suited for a seq2seq model.”
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.