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 201–300 of 1,023
Improving Bi-encoder Document Ranking Models with Two Rankers and Multi-teacher Distillation
Choi, J., Jung, E., Suh, J., & Rhee, W. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3463076 · Cited by 20
“monoBERT [13] cross-encoder CLS CEDR-KNRM [11] cross-encoder CLS,query/document TwinBERT [10] bi-encoder query/document ColBERT [8] bi-encoder CLS,query/document”
MethodEvaluating Interpolation and Extrapolation Performance of Neural Retrieval Models
Zhan, J., Xie, X., Mao, J., Liu, Y., Guo, J., Zhang, M., & Ma, S. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557312 · Cited by 37
“Weuse the authors’ open-sourced code for training ColBERT [24] and SPLADE [16].”
MethodInfluentialParameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers
Tam, W., Liu, X., Ji, K., Xue, L., Liu, J., Li, T., Dong, Y., & Tang, J. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.874 · Cited by 40
Pre-training Code Representation with Semantic Flow Graph for Effective Bug Localization
Du, Y., & Yu, Z. (2023) · Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3611643.3616338 · Cited by 19
“[40], Ciborowska et. al.”
Chakraborty, S., Chowdhury, R., Shuvo, S. R., Chatterjee, R., & Roy, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-15203-5 · Cited by 25
“Subsequent enhancements in retrieval methods, such as ColBERT 17 and hybrid approaches combining BM25 with dense retrieval 18 , further improved retrieval quality.”
Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking
Dong, Q., Liu, Y., Cheng, S., Wang, S., Cheng, Z., Niu, S., & Yin, D. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531997 · Cited by 34
“Other researches, such as RepBERT [50], ColBERT [17], COIL [11] and Interactor [49], obtain multiple vectors for query and passage for matching.”
MethodAxiomatically Regularized Pre-training for Ad hoc Search
Chen, J., Liu, Y., Fang, Y., Mao, J., Fang, H., Yang, S., Xie, X., Zhang, M., & Ma, S. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531943 · Cited by 21
Towards Imperceptible Document Manipulations against Neural Ranking Models
Chen, X., He, B., Ye, Z., Sun, L., & Sun, Y. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.416 · Cited by 39
A Question and Answering Service of Typhoon Disasters Based on the T5 Large Language Model
Xia, Y., Huang, Y., Qiu, Q., Zhang, X., Miao, L., & Chen, Y. (2024) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi13050165 · Cited by 28
“Specifically, we use the ColbertV2 (https://huggingface.co/colbert-ir/colbertv2.0 (accessed on 11 February 2024)) [55] model to convert the corpus knowledge into a vector database for storage.”
CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks
Li, X., Dou, Z., Zhou, Y., & Liu, F. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657778 · Cited by 38
Flexible retrieval with NMSLIB and FlexNeuART
Boytsov, L., & Nyberg, E. (2020) · Workshop for NLP Open Source Software (NLP-OSS) · doi:10.18653/v1/2020.nlposs-1.6 · Cited by 30
Efficient Neural Ranking using Forward Indexes
Leonhardt, J., Rudra, K., Khosla, M., Anand, A., & Anand, A. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3511955 · Cited by 28
“An alternative design strategy is to use dual-encoders to learn dense vector representations for passages or documents using contextual models [10, 17, 18].”
MethodLi, H., Zhuang, S., Mourad, A., Ma, X., Lin, J., & Zuccon, G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-99736-6_40 · Cited by 42
Li, H., Wang, W., Liu, Z., Niu, Y., Wang, H., Zhao, S., Liao, Y., Yang, W., & Liu, X. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117832 · Cited by 19
LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval
Zhang, K., Tao, C., Shen, T., Xu, C., Geng, X., Jiao, B., & Jiang, D. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543507.3583294 · Cited by 30
Towards Improving the Reliability and Transparency of ChatGPT for Educational Question Answering
Wu, Y., Henriksson, A., Duneld, M., & Nouri, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42682-7_32 · Cited by 20
OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining
Zhang, F., Shi, S., Zhu, Y., Chen, B., Cen, Y., Yu, J., Chen, Y., Wang, L., Zhao, Q., Cheng, Y., et al. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3672354 · Cited by 38
Translate-Distill: Learning Cross-Language Dense Retrieval by Translation and Distillation
Yang, E., Lawrie, D., Mayfield, J., Oard, D. W., & Miller, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56060-6_4 · Cited by 40
To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers
Li, H., Wang, S., Zhuang, S., Mourad, A., Ma, X., Lin, J., & Zuccon, G. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531884 · Cited by 30
“[27] proposed a more complex model that uses a clustering technique to model the PRF signals; this is in turn applied to the ColBERT dense retriever [11].”
MethodPre-trained Language Model-based Retrieval and Ranking for Web Search
Zou, L., Lu, W., Liu, Y., Cai, H., Chu, X., Ma, D., Shi, D., Sun, Y., Cheng, Z., Gu, S., et al. (2022) · ACM Transactions on the Web · doi:10.1145/3568681 · Cited by 24
“ColBERT [43] introduces a late interaction architecture that independently encodes the query and the document using BERT and employs a cheap yet powerful interaction step that models their ine-grained similarity.”
MethodExtractive Explanations for Interpretable Text Ranking
Leonhardt, J., Rudra, K., & Anand, A. (2022) · ACM Transactions on Information Systems · doi:10.1145/3576924 · Cited by 35
“Some of the works use dual-encoder based models to alleviate the need of document processing during inference [3, 24, 36, 45].”
BackgroundZero-shot Query Contextualization for Conversational Search
Krasakis, A. M., Yates, A., & Kanoulas, E. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531769 · Cited by 27
“To avoid any spill-over effects we perform matching only on the query tokens; we deactivate matching on the CLS , query indicator ([Q]) and expansion tokens used in the original work [14].”
InfluentialOverview of Touché 2022: Argument Retrieval
Bondarenko, A., Fröbe, M., Kiesel, J., Syed, S., Gurcke, T., Beloucif, M., Panchenko, A., Biemann, C., Stein, B., Wachsmuth, H., et al. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-13643-6_21 · Cited by 39
SpaDE: Improving Sparse Representations using a Dual Document Encoder for First-stage Retrieval
Choi, E., Lee, S., Choi, M., Ko, H., Song, Y.-I., & Lee, J. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557456 · Cited by 28
A Static Pruning Study on Sparse Neural Retrievers
Lassance, C., Lupart, S., Déjean, H., Clinchant, S., & Tonellotto, N. (2023) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3539618.3591941 · Cited by 35
“However, the ranking of documents in dense retrieval incurs significant computational costs, even if this can be reduced through approaches such as ColBERT [19, 35], or by re-ranking only a small set of candidates [29].”
C-STS: Conditional Semantic Textual Similarity
Deshpande, A., Jimenez, C., Chen, H., Murahari, V., Graf, V., Rajpurohit, T., Kalyan, A., Chen, D., & Narasimhan, K. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.345 · Cited by 51
RecJPQ: Training Large-Catalogue Sequential Recommenders
Petrov, A. V., & Macdonald, C. (2024) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3616855.3635821 · Cited by 54
“Product Quantisation is a well-established vectors compression technique, which has been shown to be successful in approximate nearest neighbour methods [12, 24, 25, 32], information retrieval [23, 29, 48] and recommender systems [3, 26, 55].”
BackgroundMethodLi, K., Zhang, J., Chen, S., Liu, H., Liu, Y., & Chen, Y. (2024) · ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA) · doi:10.1145/3650212.3680305 · Cited by 25
“Then the CVE description 𝑑 and each commit 𝑐 𝑗 ∈ 𝐶 𝑘 are encoded separately using the CR encoder to yield two sequences of vectors: We obtain the vector representations of 𝑑 𝑖 and 𝑐 𝑗 by extracting the hidden state in the last layer of the special token [CLS] at the beginning of 𝐸 ( 𝑑 𝑖…”
Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval
Jang, K.-R., Kang, J., Hong, G., Myaeng, S.-H., Park, J., Yoon, T., & Seo, H.-C. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.78 · Cited by 25
“Recent approaches to information retrieval (IR) and natural language processing (NLP) tasks adopt contextual language models (e.g., BERT (Devlin et al., 2019)), ameliorating both synonymy and pol-ysemy problems associated with words (Zhan et al., 2020; Khattab and Zaharia, 2020; Qu et al., 2021).”
BackgroundMethodInfluentialBERT-SMAP: Paying attention to Essential Terms in passage ranking beyond BERT
Lin, D., Tang, J., Li, X., Pang, K., Li, S., & Wang, T. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2021.102788 · Cited by 18
Evaluating Embedding APIs for Information Retrieval
Kamalloo, E., Zhang, X., Ogundepo, O., Thakur, N., Alfonso-Hermelo, D., Rezagholizadeh, M., & Lin, J. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-industry.50 · Cited by 37
Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval
Zhong, W., Yang, J.-H., Xie, Y., & Lin, J. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.78 · Cited by 27
Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?Preprint
Chen, X., Lakhotia, K., Oğuz, B., Gupta, A., Lewis, P., Peshterliev, S., Mehdad, Y., Gupta, S., & Yih, W.-T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.06918 · Cited by 51
“dense vectors as representations which achieves higher accuracy but is much slower (Khattab and Zaharia, 2020).”
BackgroundGuiding Retrieval Using LLM-Based Listwise Rankers
Rathee, M., MacAvaney, S., & Anand, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88708-6_15 · Cited by 40
AlzheimerRAG: Multimodal Retrieval-Augmented Generation for Clinical Use Cases
Lahiri, A. K., & Hu, Q. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7030089 · Cited by 31
Efficient Multi-vector Dense Retrieval with Bit Vectors
Nardini, F. M., Rulli, C., & Venturini, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56060-6_1 · Cited by 38
Bruch, S., Nardini, F. M., Rulli, C., & Venturini, R. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679977 · Cited by 26
“First, its effectiveness is often on par with dense retrieval —which learns dense embed-dings [12, 13, 17, 24, 26, 28, 31].”
Chakraborty, P., Alfadel, M., & Nagappan, M. (2025) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2025.3579574 · Cited by 29
Pretrained Transformers for Text Ranking: BERT and Beyond
Yates, A., Nogueira, R. F., & Lin, J. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3462812 · Cited by 22
Ensemble Distillation for BERT-Based Ranking Models
Zhuang, H., Qin, Z., Han, S., Wang, X., Bendersky, M., & Najork, M. (2021) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3471158.3472238 · Cited by 31
“There have been many studies [14, 16, 18, 27] on leveraging the power of BERT [7] to conduct text ranking tasks.”
BackgroundImproving zero-shot retrieval using dense external expansion
Wang, X., Macdonald, C., & Ounis, I. (2022) · Information Processing & Management · doi:10.1016/j.ipm.2022.103026 · Cited by 18
“Typically |𝑞| = 32, with unused query embeddings being used for ‘‘query augmentation’’, which can increase the amount of matching between queries and documents (Khattab & Zaharia, 2020).”
InfluentialLIDER: an efficient high-dimensional learned index for large-scale dense passage retrieval
Wang, Y., Ma, H., & Wang, D. Z. (2022) · Proceedings of the VLDB Endowment · doi:10.14778/3565816.3565819 · Cited by 25
“For dense retrieval, in addition to cosine similarity [14, 15, 35], inner product is another commonly used similarity metric [21, 38, 42].”
BackgroundMethodDuReader-Retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine
Qiu, Y., Li, H., Qu, Y., Chen, Y., She, Q., Liu, J., Wu, H. Y., & Wang, H. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.357 · Cited by 48
Generative Retrieval as Multi-Vector Dense Retrieval
Wu, S., Wei, W., Zhang, M., Chen, Z., Ma, J., Ren, Z., de Rijke, M., & Ren, P. (2024) · Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3626772.3657697 · Cited by 15
Max–Min semantic chunking of documents for RAG application
Kiss, C., Nagy, M., & Szilágyi, P. (2025) · Discover Computing · doi:10.1007/s10791-025-09638-7 · Cited by 18
“[21] (i.e. maximum similarity) to retrieve the 10 most relevant chunks for a given query and the same three LLM models to answer 100 multiple-choice questions based on the 3GPP specifications acquired from ref.”
Fine-grained code-comment semantic interaction analysis
Geng, M., Wang, S., Dong, D., Gu, S., Peng, F., Ruan, W., & Liao, X. (2022) · IEEE International Conference on Program Comprehension (ICPC) · doi:10.1145/3524610.3527887 · Cited by 20
“Instead of simply encoding each image or text separately to a global feature, we apply a cross-modal late interaction inspired by [13] to model the token-wise cross-modal interaction.”
MethodSLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes
Li, M., Lin, S.-C., Ma, X., & Lin, J. (2023) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3539618.3591977 · Cited by 32
“To combine the best of both worlds, models such as ColBERT [18] and COIL [9] that leverage late interaction are proposed, where the token interaction between queries and documents only happens at the last layer of contextualized embeddings.”
BackgroundMethodInfluentialRetrieval Augmented Generation with Rich Answer Encoding
Huang, W., Lapata, M., Vougiouklis, P., Papasarantopoulos, N., & Pan, J. Z. (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-main.65 · Cited by 36
“…also important in verifying and correcting the factual errors produced by LLMs (He et al., 2023; Zhao et al., 2023) However, directly training the retriever (Karpukhin et al., 2020; Khattab and Zaharia, 2020) requires a large number of annotations of gold passages according to the given questions.”
BackgroundA Reproducibility Study of PLAID
MacAvaney, S., & Tonellotto, N. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657856 · Cited by 27
“Exhaustive Search Operating Point Pareto Frontier (nprobe, t cs , ndocs)”
BackgroundInfluentialMathematical Information Retrieval: Search and Question Answering
Zanibbi, R., Mansouri, B., & Agarwal, A. K. (2025) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000095 · Cited by 24
Inflate and Shrink:Enriching and Reducing Interactions for Fast Text-Image Retrieval
Liu, H., Yu, T., & Li, P. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.772 · Cited by 19
“Recent works (Lee et al., 2018; Khattab and Zaharia, 2020; Humeau et al., 2020; Zhao et al., 2021; Lu et al., 2021) boost accuracy of embedding-based methods and maintain high efficiency through textimage interaction in the late stage.”
BackgroundMethodMatch Your Words! A Study of Lexical Matching in Neural Information Retrieval
Formal, T., Piwowarski, B., & Clinchant, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-99739-7_14 · Cited by 36
Neural text generation for query expansion in information retrieval
Claveau, V. (2021) · IEEE/WIC/ACM International Conference on Web Intelligence · doi:10.1145/3486622.3493957 · Cited by 20
Adapting Standard Retrieval Benchmarks to Evaluate Generated Answers
Arabzadeh, N., Bigdeli, A., & Clarke, C. L. A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56060-6_26 · Cited by 26
Beyond Two-Tower Matching: Learning Sparse Retrievable Cross-Interactions for Recommendation
Su, L., Fan, Y. B., Zhu, J., Xiao, X., Duan, H., Zhao, Z., Dong, Z., & Tang, R. (2023) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3539618.3591643 · Cited by 30
Prompt-Based Effective Input Reformulation for Legal Case Retrieval
Tang, Y., Qiu, R., & Li, X. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47843-7_7 · Cited by 15
CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQL
Kothyari, M., Dhingra, D., Sarawagi, S., & Chakrabarti, S. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.868 · Cited by 49
Listwise Generative Retrieval Models via a Sequential Learning Process
Tang, Y., Zhang, R., Guo, J., de Rijke, M., Chen, W., & Cheng, X. (2024) · ACM Transactions on Information Systems · doi:10.1145/3653712 · Cited by 37
“Furthermore, dual BERT architectures are used to learn dense query and document representations to support fine-grained semantic interaction [1, 33, 42, 53, 71] in dense retrieval.”
MethodPipeRAG: Fast Retrieval-Augmented Generation via Adaptive Pipeline Parallelism
Jiang, W., Zhang, S., Han, B., Wang, J., Wang, B., & Kraska, T. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709194 · Cited by 30
Fast Graph Vector Search via Hardware Acceleration and Delayed-Synchronization Traversal
Jiang, W., Hu, H., Hoefler, T., & Alonso, G. (2025) · Proceedings of the VLDB Endowment · doi:10.14778/3749646.3749655 · Cited by 22
“Visit https://creativecommons.org/licenses/by-nc-nd/4.0/ to view a copy of this license.”
InfluentialRobust Neural Information Retrieval: An Adversarial and Out-of-Distribution Perspective
Liu, Y.-A., Zhang, R., Guo, J., de Rijke, M., Fan, Y., & Cheng, X. (2025) · ACM Transactions on Information Systems · doi:10.1145/3768153 · Cited by 40
Mitigating the Position Bias of Transformer Models in Passage Re-ranking
Hofstätter, S., Lipani, A., Althammer, S., Zlabinger, M., & Hanbury, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72113-8_16 · Cited by 28
Graph-based Multilingual Product Retrieval in E-Commerce Search
Lu, H., Hu, Y., Zhao, T., Wu, T., Song, Y., & Yin, B. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-industry.19 · Cited by 23
Adversarial Domain Adaptation for Cross-lingual Information Retrieval with Multilingual BERT
Wang, R., Zhang, Z., Zhuang, F., Gao, D., Wei, Y., & He, Q. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482050 · Cited by 14
“The interaction-based method with BERT [2, 9, 11, 24, 26] takes advantage of the abundant semantic information between text pairs.”
MethodLightweight Composite Re-Ranking for Efficient Keyword Search with BERT
Yang, Y., Qiao, Y., Shao, J., Yan, X., & Yang, T. (2022) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3488560.3498495 · Cited by 24
A knowledge-enriched ensemble method for word embedding and multi-sense embedding
Fang, L., Luo, Y., Feng, K., Zhao, K., & Hu, A. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3159539 · Cited by 15
“tions with strict latency requirements [18], [19], [20].”
BackgroundThe Istella22 Dataset: Bridging Traditional and Neural Learning to Rank Evaluation
Dato, D., MacAvaney, S., Nardini, F. M., Perego, R., & Tonellotto, N. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531740 · Cited by 28
Probing BERT for Ranking Abilities
Wallat, J., Beringer, F., Anand, A., & Anand, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-28238-6_17 · Cited by 27
Learning To Locate Visual Answer In Video Corpus Using Question
Li, B., Weng, Y., Sun, B., & Li, S. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096391 · Cited by 22
“We use 16 evaluation metrics including retrieval and R@1, R@5, R@10 and MRR [18, 19], and IOU-0.”
MethodSPLADE: Sparse Lexical and Expansion Model for First Stage RankingPreprint
Formal, T., Piwowarski, B., & Clinchant, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.05720 · Cited by 39
“ColBERT [13] pushes things further: the postponed token-level Short Research Paper III SIGIR ’21, July 11–15, 2021, Virtual Event, Canada”
BackgroundVideo-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval
Reddy, A., Martin, A. A., Yang, E., Yates, A., Sanders, K., Murray, K., Kriz, R., de Melo, C. M., Durme, B. V., & Chellappa, R. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01834 · Cited by 44
“In addition to our interaction mechanism, we again take in-spiration from ColBERT [28] in our use of soft query augmentation .”
InfluentialM3DocVQA: Multi-Modal Multi-Page Multi-Document Understanding
Cho, J., Mahata, D., İrsoy, O., He, Y., & Bansal, M. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00649 · Cited by 49
Soft Prompt Decoding for Multilingual Dense Retrieval
Huang, Z., Zeng, H., Zamani, H., & Allan, J. (2023) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3539618.3591769 · Cited by 20
“document encoders, dense retrieval has already shown success on monolingual retrieval tasks [18, 29].”
BackgroundLearning Balanced Tree Indexes for Large-Scale Vector Retrieval
Li, W., Feng, C., Lian, D., Xie, Y., Liu, H., Ge, Y., & Chen, E. (2023) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3580305.3599406 · Cited by 24
Kalogeropoulos, N.-R., Kontogiannis, G., & Makris, C. H. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125771 · Cited by 13
DrugKANs: A Paradigm to Enhance Drug-Target Interaction Prediction With KANs
Fu, X., Du, Z., Chen, Y., Chen, H., Zhuo, L., Lü, A., Cao, D., & Yao, X. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3566931 · Cited by 20
“Derived from ColBERT [46], we design an FE module to improve efficiency through the interaction of granularity in the feature extraction process, and maintains a relatively simple calculation mode.”
The Devil is in the Details: Evaluating Limitations of Transformer-based Methods for Granular Tasks
Joshi, B., Shah, N., Barbieri, F., & Neves, L. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.326 · Cited by 15
BERT2DNN: BERT Distillation with Massive Unlabeled Data for Online E-Commerce Search
Jiang, Y., Shang, Y., Liu, Z., Shen, H., Xiao, Y., Xu, S., Xiong, W., Yan, W., & Jin, D. (2020) · Proceedings · doi:10.1109/icdm50108.2020.00030 · Cited by 14
MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations
Ma, X., Jiang, Y., Bách, N., Wang, T., Huang, Z., Huang, F., & Lü, W. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.205 · Cited by 19
“, 2019) to two-tower dualencoders (Khattab and Zaharia, 2020), which en-”
Multitask Fine-Tuning for Passage Re-Ranking Using BM25 and Pseudo Relevance Feedback
Kim, M., & Ko, Y. (2022) · IEEE Access · doi:10.1109/access.2022.3176894 · Cited by 14
“Recently, there have been several works about efficient ranking using the dual-encoder method [20, 21].”
BackgroundHeterogeneous Graph-based Context-aware Document Ranking
Wang, S., Dou, Z., & Zhu, Y. (2023) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3539597.3570390 · Cited by 13
SparseEmbed: Learning Sparse Lexical Representations with Contextual Embeddings for Retrieval
Kong, W., Dudek, J. M., Li, C., Zhang, M., & Bendersky, M. (2023) · Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3539618.3592065 · Cited by 14
MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders Are Better Dense Retrievers
Zhou, K., Liu, X., Gong, Y., Zhao, W. X., Jiang, D., Duan, N., & Wen, J.-R. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43415-0_37 · Cited by 19
RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
Arzanipour, A., Behnia, R., Ebrahimi, R., & Dutta, K. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00165 · Cited by 23
Iterative Self-Supervised Learning for Legal Similar Case Retrieval
Liu, Y. A., Tan, T.-P., & Zhan, X. (2024) · IEEE Access · doi:10.1109/access.2024.3358622 · Cited by 12
“In the multi-vector representation category, ColBERT [24] and Gao [25] used the MaxSim operator to compute the similarity between the query and candidate documents after encoding, while Luan [26] designed a method to mimic the queries on each of the documents by an iterative clustering process and…”
Method"In-Context Learning" or: How I learned to stop worrying and love "Applied Information Retrieval"
Parry, A., Ganguly, D., & Chandra, M. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657842 · Cited by 18
ProCIS: A Benchmark for Proactive Retrieval in Conversations
Samarinas, C., & Zamani, H. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657869 · Cited by 22
Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition
Jia, C., Luo, M., Chang, X., Dang, Z., Han, M., Wang, M., Dai, G., Dang, S., & Wang, J. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680690 · Cited by 28
“More details of the training objectives and procedures are provided in the appendix.”
Efficient Multimodal Selection for Retrieval in Knowledge-Based Visual Question Answering
Luo, L., Lai, H., Pan, Y., & Yin, J. P. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3527032 · Cited by 12
“They introduced a late-interaction mechanism [17] to perform token-level similarity calculations.”
Investigating the Scalability of Approximate Sparse Retrieval Algorithms to Massive Datasets
Bruch, S., Nardini, F. M., Rulli, C., Venturini, R., & Venuta, L. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88714-7_43 · Cited by 18
CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs
Hu, Y., Lei, Z., Dai, Z., Zhang, A., Angirekula, A., Zhang, Z., & Zhao, L. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3729920 · Cited by 24
W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering
Nian, J., Peng, Z., Wang, Q., & Fang, Y. (2025) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3731120.3744578 · Cited by 27
“…RAG, is typically either a traditional unsupervised retriever like BM25 [38] or a more advanced neural retriever, such as dense retrieval [20, 21, 32, 51], which encodes questions and passages into the same embedding space and then measures the question-passage relevance score by vector similarity.”
Multi-Vector Attention Models for Deep Re-ranking
Zhou, G., & Devlin, J. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.443 · Cited by 12
“Our approach attains comparable results to ColBERT (Khattab and Zaharia, 2020) without having to extensively pad the query with [CLS] tokens.”
BackgroundMethodResultInfluentialInteractive Query Clarification and Refinement via User Simulation
Erbacher, P., Denoyer, L., & Soulier, L. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531871 · Cited by 23
“In parallel, neural ranking models, such as [16, 19], have increased their performance due to the fine-grained capture of queries and documents semantics.”
BackgroundLearned Token Pruning in Contextualized Late Interaction over BERT (ColBERT)
Lassance, C., Maachou, M., Park, J., & Clinchant, S. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531835 · Cited by 22
Static Pruning for Multi-Representation Dense Retrieval
Acquavia, A., Macdonald, C., & Tonellotto, N. (2023) · ACM Symposium on Document Engineering (DocEng) · doi:10.1145/3573128.3604896 · Cited by 15
“In fact, in multi-representation dense retrieval systems such as ColBERT [21], the scoring function in Eq.”
BackgroundMethodInfluentialCoRT: Complementary Rankings from Transformers
Wrzalik, M., & Krechel, D. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.331 · Cited by 13
An ALBERT-based Similarity Measure for Mathematical Answer Retrieval
Reusch, A., Thiele, M., & Lehner, W. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3463023 · Cited by 13
A Modern Perspective on Query Likelihood with Deep Generative Retrieval Models
Lesota, O., Rekabsaz, N., Cohen, D., Grasserbauer, K. A., Eickhoff, C., & Schedl, M. (2021) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3471158.3472229 · Cited by 22
“For instance, the BERT model is used for document/passage retrieval through fine-tuning [31], combining them with other ranking models [27], expanding to other more efficient variations [26] or dense retrieval approaches [22, 51].”
Optimizing Dense Retrieval Model Training with Hard Negatives
Zhan, J., Mao, J., Liu, Y., Guo, J., Zhang, M., & Ma, S. (2021) · arXiv · doi:10.48550/arxiv.2104.08051 · Cited by 251
“ADORE+STAR greatly outperforms all baselines, especially the existing competitive knowledge distillation approach (TCTColBERT) and the periodic index refreshing approach (ANCE).”
Method
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.