Dense Text Retrieval Based on Pretrained Language Models: A Survey
Open accessAbstract
Text retrieval is a long-standing research topic on information seeking, where a system is required to return relevant information resources to user’s queries in natural language. From heuristic-based retrieval methods to learning-based ranking functions, the underlying retrieval models have been continually evolved with the ever-lasting technical innovation. To design effective retrieval models, a key point lies in how to learn text representations and model the relevance matching. The recent success of pretrained language models (PLM) sheds light on developing more capable text-retrieval approaches by leveraging the excellent modeling capacity of PLMs. With powerful PLMs, we can effectively learn the semantic representations of queries and texts in the latent representation space, and further construct the semantic matching function between the dense vectors for relevance modeling. Such a retrieval approach is called dense retrieval , since it employs dense vectors to represent the texts. Considering the rapid progress on dense retrieval, this survey systematically reviews the recent progress on PLM-based dense retrieval. Different from previous surveys on dense retrieval, we take a new perspective to organize the related studies by four major aspects, including architecture, training, indexing and integration, and thoroughly summarize the mainstream techniques for each aspect. We extensively collect the recent advances on this topic, and include 300+ reference papers. To support our survey, we create a website for providing useful resources, and release a code repository for dense retrieval. This survey aims to provide a comprehensive, practical reference focused on the major progress for dense text retrieval.
Integrity signals
Registry
Cites
Statistics
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?
Prior research has effectively leveraged context compression techniques such as retrieval and truncation to address long text tasks with pretrained language models.
“Prior research has effectively leveraged context compression techniques such as retrieval and truncation to address long text tasks with pretrained language models (Gong et al., 2020; Zhang et al., 2022; Zhao et al., 2022).”
From BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models (2023) · cites this paper as Zhao et al., 2022
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1× · see citing works
“, RNN and its variants [156], [157]), Transformer no longer processes the data in order, but instead introduces a new self-attention mechanism: a token attends to all the positions from the input.”
BackgroundTerm-Weighting Approaches in Automatic Text Retrieval
Salton, G., & Buckley, C. (1988) · Information Processing & Management · doi:10.1016/0306-4573(88)90021-0 · Cited by 11,421 · cited 1× · see citing works
“To construct sparse vector representations, various term weighting methods have been designed and implemented, including the classic tf-idf method [11]–[13].”
MethodIntroduction to Information Retrieval
Manning, C. D., Raghavan, P., & Schütze, H. (2008) · doi:10.1017/cbo9780511809071 · Cited by 11,288 · see citing works
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · cited 5× · see citing works
“BERT [177] on SentEval [178] and SentGLUE [165] tasks.”
BackgroundMethodInfluentialLewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821 · see citing works
A vector space model for automatic indexing
Salton, G., Wong, A., & Yang, C. S. (1975) · Communications of the ACM · doi:10.1145/361219.361220 · Cited by 7,521 · cited 1× · see citing works
“Among the early efforts, a significant achievement is the vector space model [9], [10] based on the “bagof-words” assumption, representing both documents and queries as sparse term-based vectors1.”
BackgroundProceedings of the 25th international conference on Machine learning - ICML '08
(2008) · doi:10.1145/1390156 · Cited by 6,865 · see citing works
Video Google: a text retrieval approach to object matching in videos
Sivic, & Zisserman (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238663 · Cited by 6,367 · cited 1× · see citing works
“• Clustering-based index approaches [256] partition the search space by clustering.”
BackgroundCumulated gain-based evaluation of IR techniques
Järvelin, K., & Kekäläinen, J. (2002) · ACM Transactions on Information Systems · doi:10.1145/582415.582418 · Cited by 4,841 · see citing works
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361 · see citing works
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2021) · arXiv · doi:10.48550/arxiv.2107.13586 · Cited by 4,352 · see citing works
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jegou, H. (2021) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2019.2921572 · Cited by 4,228 · see citing works
The probabilistic relevance framework: BM25 and beyond
Robertson, S., & Zaragoza, H. (2009) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000019 · Cited by 3,374 · cited 1× · see citing works
“order to better understand the underlying retrieval mechanism, probabilistic relevance frameworks have been proposed for relevance modeling, exemplified by the classic BM25 model [16], [17].”
Product Quantization for Nearest Neighbor Search
Jégou, H., Douze, M., & Schmid, C. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.57 · Cited by 2,956 · cited 2× · see citing works
“In this part, we describe a product quantization (PQ) approach [261], [262] to compressing the text embeddings and accelerating similarity compute, reducing both time and memory costs.”
MethodNatural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069 · cited 6× · see citing works
“Question answering Wikipedia Natural Questions [33] 152,148 152,148 6,515 3,610 2,681,468 Wikipedia SQuAD [55] 78,713 78,713 8,886 10,570 23,215 Wikipedia TriviaQA [56] 78,785 78,785 8,837 11,313 740K Wikipedia HotpotQA [57] 85,000 170,000 5,447 7,405 5,233,329 Web WebQuestions [58] 3,417 3,417 361 2,032 – Web Curated…”
BackgroundMethodInfluentialMalkov, Y. A., & Yashunin, D. A. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2889473 · Cited by 1,904 · cited 1× · see citing works
“Besides, HNSWlib [266] and SPTAG [267] are libraries focusing on the efficient implementation for graph-based approach.”
BackgroundUnderstanding inverse document frequency: on theoretical arguments for IDF
Robertson, S. E. (2004) · Journal of Documentation · doi:10.1108/00220410410560582 · Cited by 1,550 · cited 1× · see citing works
“To construct sparse vector representations, various term weighting methods have been designed and implemented, including the classic tf-idf method [11]–[13].”
MethodAn information-theoretic perspective of tf–idf measures
Aizawa, A. (2003) · Information Processing & Management · doi:10.1016/s0306-4573(02)00021-3 · Cited by 1,419 · see citing works
How Multilingual is Multilingual BERT?
Pires, T., Schlinger, E., & Garrette, D. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1493 · Cited by 1,351 · cited 1× · see citing works
“, mBERT [323]), and achieves performance improvement in a number of languages.”
BackgroundA Survey of Automatic Query Expansion in Information Retrieval
Carpineto, C., & Romano, G. (2012) · ACM Computing Surveys · doi:10.1145/2071389.2071390 · Cited by 1,109 · cited 1× · see citing works
“For example, we can utilize query extension or query rewriting [294] to derive better search results by reformulating the issued query.”
MethodFinetuned Language Models Are Zero-Shot Learners
Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021) · arXiv · doi:10.48550/arxiv.2109.01652 · Cited by 1,101 · see citing works
Inverted files for text search engines
Zobel, J., & Moffat, A. (2006) · ACM Computing Surveys · doi:10.1145/1132956.1132959 · Cited by 1,084 · see citing works
Wang, J., Zhang, T., Song, J., Sebe, N., & Shen, H. T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699960 · Cited by 1,034 · cited 1× · see citing works
“• Hashing-based approaches [248], [254], [255] assign vec-”
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
Fedus, W., Zoph, B., & Shazeer, N. (2021) · arXiv · doi:10.48550/arxiv.2101.03961 · Cited by 1,005 · see citing works
On Relevance, Probabilistic Indexing and Information Retrieval
Maron, M. E., & Kuhns, J. L. (1960) · Journal of the ACM · doi:10.1145/321033.321035 · Cited by 908 · cited 22× · see citing works
“Unlike sparse retrievers (e.g., BM25), dense retrievers no longer rely on exact term matching for text retrieval, but instead learn semantic matching for capturing the text relevance.”
BackgroundInfluentialAlfredo Cuzzocrea, J. A., Cuzzocrea, A., Allan, J., Paton, N. W., Srivastava, D., Agrawal, R., Broder, A., Zaki, M. J., Selçuk Candan, K., Labrinidis, A., et al. (2006) · doi:10.1145/1183614 · Cited by 756 · see citing works
Perego, R., Sebastiani, F., Aslam, J., Ruthven, I., & Zobel, J. (2016) · doi:10.1145/2911451 · Cited by 726 · see citing works
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics
Heafield, K. (2016) · The Association for Computational Linguistics · Cited by 718 · see citing works
Text and Code Embeddings by Contrastive Pre-TrainingPreprint
Neelakantan, A., Xu, T., Puri, R., Radford, A., Han, J. M., Tworek, J., Yuan, Q.-M., Tezak, N., Kim, J. W., Hallacy, C., et al. (2022) · arXiv.org · doi:10.48550/arxiv.2201.10005 · Cited by 657 · cited 1× · see citing works
“Besides, it has shown that unsupervised contrastive pretraining [245] (pretraining with text pairs and text-code pairs) can also improve both text and code retrieval performance.”
BackgroundTsatsaronis, G., Balikas, G., Malakasiotis, P., Partalas, I., Zschunke, M., Alvers, M. R., Weissenborn, D., Krithara, A., Petridis, S., Polychronopoulos, D., et al. (2015) · BMC Bioinformatics · doi:10.1186/s12859-015-0564-6 · Cited by 598 · cited 3× · see citing works
“constructed based on lexical matching models [47], [61], they tend to be more favorable for sparse retrieval methods due to a larger term overlap.”
BackgroundA Survey on Dialogue Systems: Recent Advances and New Frontiers
Chen, H., Liu, X., Yin, D., & Tang, J. (2017) · ACM SIGKDD Explorations Newsletter · doi:10.1145/3166054.3166058 · Cited by 579 · cited 1× · see citing works
“As one of the most essential techniques to overcome information overload, text retrieval systems have been widely employed to support many downstream applications, including question answering [1], [2], dialog system [3], [4], entity linking [5], [6] and Web search [7].”
BackgroundSPECTER: Document-level Representation Learning using Citation-informed Transformers
Cohan, A., Feldman, S., Beltagy, I., Downey, D., & Weld, D. S. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.207 · Cited by 572 · see citing works
Li, W., Zhang, Y., Sun, Y., Wang, W., Li, M., Zhang, W., & Lin, X. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2909204 · Cited by 501 · see citing works
Learning to Match using Local and Distributed Representations of Text for Web Search
Mitra, B., Díaz, F., & Craswell, N. (2017) · International World Wide Web Conference (WWW) · doi:10.1145/3038912.3052579 · Cited by 458 · cited 1× · see citing works
“As one of the most essential techniques to overcome information overload, text retrieval systems have been widely employed to support many downstream applications, including question answering [1], [2], dialog system [3], [4], entity linking [5], [6] and Web search [7].”
BackgroundIn-Context Retrieval-Augmented Language Models
Ram, O., Levine, Y., Dalmedigos, I., Muhlgay, D., Shashua, A., Leyton-Brown, K., & Shoham, Y. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00605 · Cited by 449 · see citing works
Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models
Ni, J., Ábrego, G. H., Constant, N., Ma, J., Hall, K., Cer, D. M., & Yang, Y. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.146 · Cited by 449 · see citing works
Test Collection Based Evaluation of Information Retrieval Systems
Sanderson, M. (2010) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000009 · Cited by 447 · cited 1× · see citing works
“discussion about IR evaluation, the readers are suggested to read more focused references [75], [76], [79], [80].”
BackgroundVideo google: A text retrieval approach to object matching in videos
Sivic, J., & Zisserman, A. (2003) · Cited by 438 · see citing works
SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking
Formal, T., Piwowarski, B., & Clinchant, S. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3463098 · Cited by 427 · see citing works
Approximate nearest neighbor algorithm based on navigable small world graphs
Malkov, Y. A., Ponomarenko, A., Logvinov, A., & Krylov, V. (2013) · Information Systems · doi:10.1016/j.is.2013.10.006 · Cited by 418 · see citing works
Bouma, G., & Parmentier, Y. (2023) · doi:10.18653/v1/2023.eacl-main · Cited by 384 · see citing works
Improving language models by retrieving from trillions of tokens
Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., Driessche, G. V. D., Lespiau, J.-B., Damoc, B., Clark, A., et al. (2021) · arXiv · doi:10.48550/arxiv.2112.04426 · Cited by 382 · cited 2× · see citing works
“In order to alleviate this issue, retrieval-augmented LMs have been proposed by allowing the model to explicitly access external data [94], [313]–[316].”
BackgroundMethodA Deep Look into neural ranking models for information retrieval
Guo, J., Fan, Y., Pang, L., Yang, L., Ai, Q., Zamani, H., Wu, C. H., Croft, W. B., & Cheng, X. (2019) · Information Processing & Management · doi:10.1016/j.ipm.2019.102067 · Cited by 380 · cited 3× · see citing works
“We are aware of several closely related surveys or books on dense retrieval [24]–[26], [29], [35].”
BackgroundSparse, Dense, and Attentional Representations for Text Retrieval
Luan, Y., Eisenstein, J., Toutanova, K., & Collins, M. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00369 · Cited by 363 · cited 5× · see citing works
“A straightforward approach is to aggregate the retrieval scores of the two approaches [1], [96].”
BackgroundMethodInfluentialColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
Santhanam, K., Khattab, O., Saad-Falcon, J., Potts, C., & Zaharia, M. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.272 · Cited by 353 · see citing works
Inverted files versus signature files for text indexing
Zobel, J., Moffat, A., & Ramamohanarao, K. (1998) · ACM Transactions on Database Systems · doi:10.1145/296854.277632 · Cited by 343 · cited 1× · see citing works
“Such a representation scheme is further supported by the well-known data structure of inverted index [14], [15], which organizes the text content”
MethodEfficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling
Hofstätter, S., Lin, S.-C., Yang, J.-H., Lin, J., & Hanbury, A. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3462891 · Cited by 318 · see citing works
Autoregressive Entity RetrievalPreprint
Cao, N. D., Izacard, G., Riedel, S., & Petroni, F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.00904 · Cited by 307 · cited 1× · see citing works
“Indeed, the idea of generative retrieval has been first explored in the task of entity linking [299], where entity identifiers (e.”
BackgroundZhao, Z., Du, L., Börschinger, B., Pate, J. K., Ciaramita, M., Steedman, M. J., & Johnson, M. (2015) · The Association for Computational Linguistics · Cited by 275 · see citing works
Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents
Sun, W., Yan, L., Ma, X., Wang, S., Ren, P., Chen, Z., Yin, D., & Ren, Z. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.923 · Cited by 270 · see citing works
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 · cited 4× · see citing works
“, a sampler over the text collection based on some relevance model) is fixed or updated, hard negatives can be roughly divided into static hard negatives and dynamic hard negatives [98], [111].”
BackgroundMethodInfluentialUnsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval
Gao, L., & Callan, J. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.203 · Cited by 251 · see citing works
Learning to Rank for Information Retrieval and Natural Language Processing
Li, H. (2011) · Synthesis lectures on human language technologies · doi:10.2200/s00348ed1v01y201104hlt012 · Cited by 249 · see citing works
Optimizing Dense Retrieval Model Training with Hard Negatives
Zhan, J., Mao, J., Liu, Y., Guo, J., Zhang, M., & Ma, S. (2021) · Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3404835.3462880 · Cited by 248 · cited 4× · see citing works
“, a sampler over the text collection based on some relevance model) is fixed or updated, hard negatives can be roughly divided into static hard negatives and dynamic hard negatives [98], [111].”
BackgroundMethodInfluentialStatistical language models for information retrieval
Zhai, C. (2007) · doi:10.3115/1614181.1614183 · Cited by 216 · see citing works
Learning Dense Representations for Entity Retrieval
Gillick, D., Kulkarni, S., Lansing, L., Presta, A., Baldridge, J., Ie, E., & García-Olano, D. (2019) · Conference on Computational Natural Language Learning · doi:10.18653/v1/k19-1049 · Cited by 215 · cited 2× · see citing works
“As one of the most essential techniques to overcome information overload, text retrieval systems have been widely employed to support many downstream applications, including question answering [1], [2], dialog system [3], [4], entity linking [5], [6] and Web search [7].”
BackgroundMethodSynthetic QA Corpora Generation with Roundtrip Consistency
Alberti, C., Andor, D., Pitler, E., Devlin, J., & Collins, M. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1620 · Cited by 208 · cited 2× · see citing works
“[227] propose a pipeline approach to constructing question-answer pairs from large text corpora.”
BackgroundUnderstanding the Behaviors of BERT in Ranking
Qiao, Y., Xiong, C., Liu, Z., & Liu, Z. (2019) · arXiv · doi:10.48550/arxiv.1904.07531 · Cited by 201 · cited 2× · see citing works
“To implement the reranker, a typical approach is to employ the cross-encoder as the ranking model, showing substantial improvements over the traditional methods [193], [272]–[274].”
MethodPretrained Transformers for Text Ranking: BERT and Beyond
Yates, A., Nogueira, R. F., & Lin, J. (2021) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3437963.3441667 · Cited by 183 · cited 10× · see citing works
“[25] present a review of text ranking methods mainly based on pretrained Transformers, Fan et al.”
BackgroundMethodInfluential(2022) · doi:10.18653/v1/2022.emnlp-main.669 · Cited by 177 · see citing works
Lin, J., & Ma, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.14807 · Cited by 154 · cited 3× · see citing works
“[170] propose a conceptual framework to unify these approaches: DeepCT aims to assign scalar weights to query terms, while COIL aims to assign vector weights to query terms.”
BackgroundMethodInfluentialPAQ: 65 Million Probably-Asked Questions and What You Can Do With Them
Lewis, P., Wu, Y., Liu, L., Minervini, P., Küttler, H., Piktus, A., Stenetorp, P., & Riedel, S. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00415 · Cited by 153 · cited 2× · see citing works
“[228] further introduce passage selection and global filtering to construct a dataset called PAQ for question answering, which contains 65 million synthetically generated question-answer pairs from Wikipedia.”
BackgroundSemantic term matching in axiomatic approaches to information retrieval
Fang, H., & Zhai, C. (2006) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/1148170.1148193 · Cited by 129 · cited 1× · see citing works
“Another possible approach to understanding the behavior of dense retrievers is axiomatic analysis from classic IR literature [196]–[198].”
BackgroundTransformer Memory as a Differentiable Search Index
Tay, Y., Tran, V., Dehghani, M., Ni, J., Bahri, D., Mehta, H., Qin, Z., Hui, K., Zhao, Z., Gupta, J., et al. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1587 · Cited by 128 · see citing works
mMARCO: A Multilingual Version of the MS MARCO Passage Ranking DatasetPreprint
Bonifacio, L., Jeronymo, V., Abonizio, H. Q., Campiotti, I., Fadaee, M., Lotufo, R., & Nogueira, R. F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.13897 · Cited by 126 · cited 3× · see citing works
“Information retrieval Web MS MARCO [32] 502,939 532,761 6,980 6,837 8,841,823 Web mMARCO [44] 808,731 – 101,093 – 8,841,823 News TREC-NEWS [43] – – – 57 594,977 Biomedical TREC-COVID [45] – – – 50 171,332 Biomedical NFCorpus [46] 5,922 110,575 324 323 3,633 Twitter Signal-1M [47] – – – 97 2,866,316 Argument Touché-202…”
MethodTREC-COVID: rationale and structure of an information retrieval shared task for COVID-19
Roberts, K. E., Alam, T., Bedrick, S. D., Demner‐Fushman, D., Lo, K., Soboroff, I. M., Voorhees, E. M., Wang, L. L., & Hersh, W. (2020) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaa091 · Cited by 123 · cited 2× · see citing works
“Information retrieval Web MS MARCO [32] 502,939 532,761 6,980 6,837 8,841,823 Web mMARCO [44] 808,731 – 101,093 – 8,841,823 News TREC-NEWS [43] – – – 57 594,977 Biomedical TREC-COVID [45] – – – 50 171,332 Biomedical NFCorpus [46] 5,922 110,575 324 323 3,633 Twitter Signal-1M [47] – – – 97 2,866,316 Argument Touché-202…”
BackgroundRethinking search: making domain experts out of dilettantes
Metzler, D., Tay, Y., Bahri, D., & Najork, M. (2021) · ACM SIGIR Forum · doi:10.1145/3476415.3476428 · Cited by 112 · see citing works
InPars: Unsupervised Dataset Generation for Information Retrieval
Bonifacio, L., Abonizio, H., Fadaee, M., & Nogueira, R. F. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531863 · Cited by 108 · see citing works
Information Retrieval Evaluation
Harman, D. K. (2011) · Synthesis lectures on information concepts, retrieval, and services · doi:10.1007/978-3-031-02276-0 · Cited by 103 · see citing works
Pretrained Transformers for Text Ranking: BERT and BeyondPreprint
Lin, J., Nogueira, R. F., & Yates, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.06467 · Cited by 101 · cited 10× · see citing works
“[25] present a review of text ranking methods mainly based on pretrained Transformers, Fan et al.”
BackgroundMethodInfluentialRankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses
Zhuang, H., Qin, Z., Jagerman, R., Hui, K., Ma, J., Lu, J. R., Ni, J., Wang, X., & Bendersky, M. (2023) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3539618.3592047 · Cited by 96 · cited 1× · see citing works
“outputs the relevance label [41] or ranking score [278].”
BackgroundInformation Retrieval Evaluation
Harman, D. K. (2011) · Synthesis lectures on information concepts, retrieval, and services · doi:10.2200/s00368ed1v01y201105icr019 · Cited by 92 · see citing works
Learning to Rank for Information Retrieval and Natural Language Processing
Li, H. (2011) · Synthesis lectures on human language technologies · doi:10.1007/978-3-031-02141-1 · Cited by 91 · cited 1× · see citing works
“With the development of machine learning discipline, learning to rank [19], [20] introduces supervised learning for text ranking.”
BackgroundGPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval
Wang, K., Thakur, N., Reimers, N., & Gurevych, I. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.168 · Cited by 83 · see citing works
Autoregressive Search Engines: Generating Substrings as Document Identifiers
Bevilacqua, M., Ottaviano, G., Lewis, P., Yih, S., Riedel, S., & Petroni, F. (2022) · neural information processing systems · doi:10.52202/068431-2296 · Cited by 80 · see citing works
Query-driven iterated neighborhood graph search for large scale indexing
Wang, J., & Li, S. (2012) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2393347.2393378 · Cited by 71 · see citing works
SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval
Wang, L., Yang, N., Huang, X., Jiao, B., Yang, L., Jiang, D., Majumder, R., & Wei, F. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.125 · Cited by 71 · see citing works
Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval
Wang, X., Macdonald, C., Tonellotto, N., & Ounis, I. (2021) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3471158.3472250 · Cited by 68 · cited 1× · see citing works
“[190] employ relevance feedback to enhance the multi-representation dense retrieval models, showing a large performance improvement over the base model ColBERT.”
MethodMr. TyDi: A Multi-lingual Benchmark for Dense Retrieval
Zhang, X., Ma, X., Shi, P., & Lin, J. (2021) · Workshop on Multilingual Representation Learning (MRL) · doi:10.18653/v1/2021.mrl-1.12 · Cited by 65 · see citing works
Pre-trained Language Model for Web-scale Retrieval in Baidu Search
Liu, Y., Lu, W., Cheng, S., Shi, D., Wang, S., Cheng, Z., & Yin, D. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467149 · Cited by 60 · cited 3× · see citing works
“3), an integration of dense retrieval and sparse retrieval techniques has been employed in Baidu search [345] and Spotify search27.”
MethodA Length-Extrapolatable Transformer
Sun, Y., Dong, L., Patra, B., Ma, S., Huang, S., Benhaim, A., Chaudhary, V., Song, X., & Wei, F. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.816 · Cited by 59 · see citing works
Adaptive Semiparametric Language Models
Yogatama, D., d’Autume, C. D. M., & Kong, L. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00371 · Cited by 58 · cited 1× · see citing works
“[315] incorporate a gating mechanism to replace the fixed interpolation parameter in kNN-LM, which adaptively combines short-term memory with long-term memory (i.”
BackgroundCorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks
Chen, J., Zhang, R., Guo, J., Liu, Y., Fan, Y., & Cheng, X. (2022) · Proceedings of the 31st ACM International Conference on Information & Knowledge Management · doi:10.1145/3511808.3557271 · Cited by 57 · see citing works
MS MARCO: Benchmarking Ranking Models in the Large-Data Regime
Craswell, N., Mitra, B., Yılmaz, E., Campos, D., & Lin, J. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3462804 · Cited by 56 · cited 1× · see citing works
“A recent study [70] has summarized the promotion effect of MS MARCO on the progress of dense retrieval: “the MS MARCO datasets have enabled large-data exploration of neural models”.”
BackgroundThe thesaurus approach to information retrieval
Joyce, T., & Needham, R. M. (1958) · American Documentation · doi:10.1002/asi.5090090305 · Cited by 55 · see citing works
Shallow pooling for sparse labels
Arabzadeh, N., Vtyurina, A., Yan, X., & Clarke, C. L. A. (2022) · Information Retrieval · doi:10.1007/s10791-022-09411-0 · Cited by 54 · cited 2× · see citing works
“This issue becomes more severe for hard negatives, which are more likely to be false negatives [74], [214], [215] (i.”
BackgroundMulti-Task Retrieval for Knowledge-Intensive Tasks
Maillard, J., Karpukhin, V., Petroni, F., Yih, W.-T., Oğuz, B., Stoyanov, V., & Ghosh, G. (2021) · Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2021.acl-long.89 · Cited by 49 · see citing works
Joint Learning of Deep Retrieval Model and Product Quantization based Embedding Index
Zhang, H., Shen, H., Qiu, Y., Jiang, Y., Wang, S., Xu, S., Xiao, Y., Long, B., & Yang, W.-Y. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3462988 · Cited by 47 · cited 2× · see citing works
“[263] also propose several improved optimization strategies (including gradient straight-through estimators, warm start centroids and Givens rotation) to jointly train deep retrieval models with quantization based embedding index.”
BackgroundEvaluating the Robustness of Retrieval Pipelines with Query Variation Generators
Penha, G., Câmara, A., & Hauff, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-99736-6_27 · Cited by 47 · see citing works
Domain-matched Pre-training Tasks for Dense Retrieval
Oğuz, B., Lakhotia, K., Gupta, A., Lewis, P., Karpukhin, V., Piktus, A., Chen, X., Riedel, S., Yih, S., Gupta, S., et al. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.114 · Cited by 46 · see citing works
Proceedings of the 20th Australasian Document Computing Symposium
(2015) · doi:10.1145/2838931 · Cited by 45 · see citing works
Promptagator: Few-shot Dense Retrieval From 8 Examples
Dai, Z., Zhao, V. Y., Ma, J., Luan, Y., Ni, J., Lu, J., Bakalov, A., Guu, K., Hall, K. B., & Chang, M.-W. (2022) · arXiv · doi:10.48550/arxiv.2209.11755 · Cited by 43 · cited 3× · see citing works
“Recently, Promptagator [153] leverages a large language model consisting of 137 billion parameters, i.”
BackgroundMethodDealing with Typos for BERT-based Passage Retrieval and Ranking
Zhuang, S., & Zuccon, G. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.225 · Cited by 42 · cited 4× · see citing works
“[291] propose a typos-aware training approach, which changes the queries”
BackgroundMethodInfluentialPredicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selection
Arabzadeh, N., Yan, X., & Clarke, C. L. A. (2021) · Proceedings of the 30th ACM International Conference on Information & Knowledge Management · doi:10.1145/3459637.3482159 · Cited by 41 · see citing works
Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
Chen, X., Lakhotia, K., Oğuz, B., Gupta, A., Lewis, P., Peshterliev, S., Mehdad, Y., Gupta, S., & Yih, W.-T. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.19 · Cited by 40 · see citing works
Magnani, A., Liu, F., Chaidaroon, S., Yadav, S., Suram, P. R., Puthenputhussery, A., Chen, S., Xie, M., Kashi, A., Lee, T., et al. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539164 · Cited by 37 · cited 3× · see citing works
“[282] design a dense-sparse hybrid system for e-commerce search deployed at Walmart, and they select negatives based on three strategies including product type matching, query”
BackgroundMethodOne Question Answering Model for Many Languages with Cross-lingual Dense Passage RetrievalPreprint
Asai, A., Yu, X., Kasai, J., & Hajishirzi, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.11976 · Cited by 36 · cited 1× · see citing works
“[322] further propose a multilingual dense passage retriever that extends DPR to retrieve candidate passages from multilingual document collections in a cross-lingual way.”
BackgroundLearning to retrieve passages without supervision
Ram, O., Shachaf, G., Levy, O., Berant, J., & Globerson, A. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.193 · Cited by 35 · see citing works
Diagnosing BERT with Retrieval Heuristics
Câmara, A., & Hauff, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-45439-5_40 · Cited by 32 · cited 1× · see citing works
“However, it has been found that existing IR axioms may only partially explain [200] or even not be suitable to analyze [201] the behavior of PLM-based IR models.”
BackgroundQue2Search: Fast and Accurate Query and Document Understanding for Search at Facebook
Liu, Y., Rangadurai, K., He, Y., Malreddy, S., Gui, X., Liu, X., & Borisyuk, F. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467127 · Cited by 32 · cited 2× · see citing works
“[348] incorporate the embeddings of product images as the input of dense retriever.”
MethodUni-Retriever: Towards Learning the Unified Embedding Based Retriever in Bing Sponsored Search
Zhang, J., Liu, Z., Han, W., Xiao, S., Zheng, R., Shao, Y., Sun, H., Zhu, H., Srinivasan, P., Deng, W., et al. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539212 · Cited by 31 · see citing works
Tevatron: An Efficient and Flexible Toolkit for Dense RetrievalPreprint
Gao, L., Ma, X., Lin, J., & Callan, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.05765 · Cited by 27 · cited 2× · see citing works
“It can be accessed at the link: https://github.com/TextTron/Tevatron.”
MethodProceedings of the 2021 ACM SIGIR International Conference on Theory of Information Retrieval
Hasibi, F., Fang, Y., & Aizawa, A. (2021) · doi:10.1145/3471158 · Cited by 27 · see citing works
xMoCo: Cross Momentum Contrastive Learning for Open-Domain Question Answering
Yang, N., Wei, F., Jiao, B., Jiang, D., & Yang, L. (2021) · doi:10.18653/v1/2021.acl-long.477 · Cited by 26 · cited 1× · see citing works
“Similar symmetric optimization tricks have been used in a number of follow-up studies [115], [132], [209], [210], showing an improved retrieval performance.”
BackgroundChallenges in Generalization in Open Domain Question Answering
Liu, L., Lewis, P., Riedel, S., & Stenetorp, P. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.155 · Cited by 26 · see citing works
PROD: Progressive Distillation for Dense Retrieval
Lin, Z., Gong, Y., Liu, X., Zhang, H., Lin, C., Dong, A., Jiao, J., Lu, J., Jiang, D., Majumder, R., et al. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543507.3583421 · Cited by 26 · cited 4× · see citing works
“PROD [154] proposes to use a progressive chain of the teacher model with improved model architectures and increased network layers: 12-layer bi-encoder → 12layer cross-encoder → 24-layer cross-encoder (given the 6layer bi-encoder as the student model).”
MethodInfluentialLearning Robust Dense Retrieval Models from Incomplete Relevance Labels
Prakash, P., Killingback, J., & Zamani, H. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3463106 · Cited by 25 · cited 2× · see citing works
“index 2021 Condenser [112] Condenser SR CE IB REP 2021 DRPQ [113] BERTbase MR NLL IB+DyHN Multiple pseudo query embeddings 2021 RANCE [114] RoBERTabase SR NLL DeHN 2021 DANCE [115] RoBERTabase SR IOC SHN Contrastive dual learning 2021 DPR-PAQ [116] RoBERTalarge SR NLL IB+SHN ALD GAP 2021 JPQ [117] BERTbase SR IOC DyHN…”
BackgroundMethodWang, J., Jatowt, A., & Yoshikawa, M. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531734 · Cited by 22 · see citing works
Towards Robust Ranker for Text Retrieval
Zhou, Y., Shen, T., Geng, X., Tao, C., Xu, C., Long, G., Jiao, B., & Jiang, D. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.332 · Cited by 20 · see citing works
Parameter-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 20 · see citing works
Self-citationLED: 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 18 · cited 3× · see citing works
“Besides, LED [151] proposes to employ PLM-based lexical-aware models (i.”
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 18 · see citing works
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 17 · see citing works
DuReader-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 16 · see citing works
Self-citationMulti-modal Retrieval of Tables and Texts Using Tri-encoder Models
Kostić, B., Risch, J., & Möller, T. (2021) · Workshop on Machine Reading for Question Answering (MRQA) · doi:10.18653/v1/2021.mrqa-1.8 · Cited by 16 · see citing works
CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training
Huber, P., Aghajanyan, A., Oğuz, B., Okhonko, D., Yih, S., Gupta, S., & Chen, X. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.184 · Cited by 14 · see citing works
Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor SearchPreprint
Simhadri, H. V., Williams, G., Aumüller, M., Douze, M., Babenko, A., Baranchuk, D., Chen, Q., Hosseini, L., Krishnaswamy, R., Srinivasa, G., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.03763 · Cited by 14 · cited 1× · see citing works
“In order to evaluate different ANNS aglorithms, ANN-Benchmarks [252]18 has been released with a millionscale benchmark, and an enlarged version called Big-ANNBenchmarks [253]19 further extends the data size to a billion scale.”
MethodSetRank: Learning a Permutation-Invariant Ranking Model for Information RetrievalPreprint
Pang, L., Xu, J., Ai, Q., Lan, Y., Cheng, X., & Wen, J.-R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.05891 · Cited by 14 · cited 2× · see citing works
“A similar approach SetRank [280] has been proposed, though it does not use PLMs.”
MethodSelf-citationImplicit Feedback for Dense Passage Retrieval
Zhuang, S., Li, H., & Zuccon, G. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531994 · Cited by 10 · cited 1× · see citing works
“[189] explore click-through data as feedback signal by using simulation based on click models, and then propose a counterfactual approach to dealing with the bias issue in click data.”
MethodLewis, P., Oğuz, B., Xiong, W., Petroni, F., Yih, S., & Riedel, S. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.226 · Cited by 10 · see citing works
An inverted index implementation
McDonell, K. J. (1977) · The Computer Journal · doi:10.1093/comjnl/20.2.116 · Cited by 10 · cited 1× · see citing works
“In essence, inverted index maintains an efficient mapping from terms to their locations in documents [247].”
BackgroundDynamicRetriever: A Pre-training Model-based IR System with Neither Sparse nor Dense IndexPreprint
Zhou, Y., Yao, J., Dou, Z., Wu, L., & Wen, J.-R. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.00537 · Cited by 10 · cited 2× · see citing works
“, passage, word sets and ngrams [301], [305]) or associated content (e.”
BackgroundMethodSelf-citationHLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer RerankingPreprint
Zhang, Y., Long, D., Xu, G., & Xie, P. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.10569 · Cited by 10 · cited 1× · see citing works
“chitecture has been proposed [279] for multi-stage ranking optimization 22.”
BackgroundHofstätter, S., Khattab, O., Althammer, S., Sertkan, M., & Hanbury, A. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.13088 · Cited by 7 · cited 6× · see citing works
“Considering this issue, some specific strategies proposed in ColBERTer [136] can be used to reduce the multi-representation costs, such as embedding”
BackgroundMethodInfluentialCheng, H., Fang, H., Liu, X., & Gao, J. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-short.159 · Cited by 6 · see citing works
(2022) · doi:10.1145/3477495.3531658 · Cited by 6 · cited 2× · see citing works
“An important merit is that the training can be decoupled from checkpoint validation with Asyncval.”
MethodSimple and Efficient ways to Improve REALM
Balachandran, V., Vaswani, A., Tsvetkov, Y., & Parmar, N. (2021) · Workshop on Machine Reading for Question Answering (MRQA) · doi:10.18653/v1/2021.mrqa-1.16 · Cited by 5 · see citing works
Densifying Sparse Representations for Passage Retrieval by Representational SlicingPreprint
Lin, S.-C., & Lin, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.04666 · Cited by 5 · cited 2× · see citing works
“[147], [206] propose to learn low-dimensional dense lexical representations (DLRs) by densifying high-dimensional sparse lexical representations, making it feasible to end-to-end learn lexical-semantic combined retrieval systems.”
BackgroundZhan, J., Mao, J., Liu, Y., Guo, J., Zhang, M., & Ma, S. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/754 · Cited by 4 · see citing works
Hofstätter, S., Craswell, N., Mitra, B., Zamani, H., & Hanbury, A. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.12993 · Cited by 2 · cited 2× · see citing works
“Besides the effectiveness, the cost for maintenance and use is also important to consider for the practical deployment of dense retrieval systems [350].”
BackgroundBoosted Dense RetrieverPreprint
Lewis, P., Oğuz, B., Xiong, W., Petroni, F., Yih, W.-T., & Riedel, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.07771 · Cited by 1 · cited 2× · see citing works
“training + Mutual distillation 2021 AR2-G [121] ERNIEbase SR IOC DyHN Adversarial training 2021 RepCONC [122] BERTbase SR IOC DyHN Quantization 2021 RocketQAv2 [38] ERNIEbase SR KL SHN+DeHN KD Joint training + Mutual distillation 2021 SPAR [123] BERTbase SR NLL SHN KD 2021 SEED [124] BERTbase SR NLL DyHN TAP Autoencod…”
BackgroundMethod
Flagged first, then by citations
2 of the 156 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3703155 · Cited by 2,142 · see citing works
A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4
Kalyan, K. S. (2024) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100048 · Cited by 335 · see citing works
Large Language Models for Information Retrieval: A Survey
Zhu, Y., Yuan, H., Wang, S., Liu, J., Liu, W., Deng, C., Chen, H., Liu, Z., Dou, Z., & Wen, J.-R. (2026) · ACM Transactions on Information Systems · doi:10.1145/3748304 · Cited by 225 · see citing works
“In recent years, the neural IR [30, 55, 56] paradigm has gained considerable”
Self-citationHuang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.05232 · Cited by 2,516 · see citing works
Cross-Modal Retrieval: A Systematic Review of Methods and Future Directions
Wang, T., Li, F., Zhu, L., Li, J., Zhang, Z., & Shen, H. T. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3525147 · Cited by 134 · see citing works
A Survey on Retrieval-Augmented Text Generation for Large Language Models
Huang, Y., & Huang, J. X. (2026) · ACM Computing Surveys · doi:10.1145/3805774 · Cited by 185 · see citing works
When Search Engine Services Meet Large Language Models: Visions and Challenges
Xiong, H., Bian, J., Li, Y., Li, X., Du, M., Wang, S., Yin, D., & Helal, S. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3451185 · Cited by 82 · see citing works
“By providing high-quality, relevance-annotated query-webpage pairs, LLMs ensure that the training data for information retrieval neural networks is both accurate and representative of diverse query intents and informational needs [117], [134], [135].”
A Literature Survey on Open Source Large Language Models
Kukreja, S., Kumar, T., Purohit, A., Dasgupta, A., & Guha, D. (2024) · International Conference on Computers in Management and Business (ICCMB) · doi:10.1145/3647782.3647803 · Cited by 65 · see citing works
Industrial Foundation Models (IFMs) for intelligent manufacturing: A systematic review
Zhao, S., Liu, S., Jiang, Y., Zhao, B. M., Lv, Y., Zhang, J., Wang, L., & Zhong, R. Y. (2025) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2025.06.011 · Cited by 46 · see citing works
Continual Learning for Generative Retrieval over Dynamic Corpora
Chen, J., Zhang, R., Guo, J., de Rijke, M., Chen, W., Fan, Y., & Cheng, X. (2023) · Proceedings of the 32nd ACM International Conference on Information and Knowledge Management · doi:10.1145/3583780.3614821 · Cited by 40 · see citing works
“One is to generate docids for documents [53] including atomic identifiers (e.”
BackgroundHuang, X., Liu, Z. Y., Zhang, M., 桂, 韬., 韩, 先., 户, 保., 黄, 民., 黄, 萱., 刘, 康., 刘, 挺., et al. (2023) · Scientia Sinica Informationis · doi:10.1360/ssi-2023-0113 · Cited by 40 · see citing works
An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities
Yang, Z., Chen, S., Gao, C., Li, Z., Hu, X., Liu, K., & Xia, X. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3717061 · Cited by 37 · see citing works
Large Language Models are Built-in Autoregressive Search Engines
Ziems, N., Yu, W., Zhang, Z., & Jiang, M. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.167 · Cited by 39 · see citing works
A Thorough Examination on Zero-shot Dense Retrieval
Ren, R., Qu, Y., Liu, J., Zhao, X., Wu, Q., Ding, Y., Wu, H. Y., Wang, H., & Wen, J.-R. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.1057 · Cited by 34 · see citing works
Self-citationTravelRAG: A Tourist Attraction Retrieval Framework Based on Multi-Layer Knowledge Graph
Song, S., Yang, C., Li, X., Shang, H., Li, Z., & Chang, Y. (2024) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi13110414 · Cited by 25 · see citing works
Leveraging LLMs for Unsupervised Dense Retriever Ranking
Khramtsova, E., Zhuang, S., Baktashmotlagh, M., & Zuccon, G. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657798 · Cited by 23 · see citing works
“In contrast, our unsupervised approach (indicated by red squares) consistently selects competitive models across various collections, and even identifies the most performant model for Trec-News.”
Equipping Llama with Google Query API for Improved Accuracy and Reduced HallucinationPreprint
Bae, Y. S., Kim, H. R., & Kim, J. H. (2024) · Research Square · doi:10.21203/rs.3.rs-4014474/v1 · Cited by 19 · see citing works
Bridging Modalities: Improving Universal Multimodal Retrieval by Multimodal Large Language Models
Zhang, X., Zhang, Y., Xie, W., Li, M., Dai, Z., Long, D., Xie, P., Zhang, M., Li, W., & Zhang, M. (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/cvpr52734.2025.00866 · Cited by 62 · see citing works
“Multimodal Retrieval Early multimodal retrieval tasks focused on single-modal [73] or cross-modal retrieval [61].”
Generative Retrieval via Term Set Generation
Zhang, P., Liu, Z., Zhou, Y., Dou, Z., Liu, F., & Cao, Z. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657797 · Cited by 27 · see citing works
“Document retrieval, standing as the most representative form of information retrieval, is fundamentally important to real-world applications like web search, question answering, advertising, and recommendation [17, 56].”
BackgroundMultimodal Integration in Large Language Models: A Case Study with Mistral LLMPreprint
Sulaiman, N., & Hamzah, F. (2024) · doi:10.31219/osf.io/9y5ds · Cited by 17 · see citing works
REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing
Chen, K., Nadig, R., Frouzakis, M., Ghiasi, N. M., Liang, Y., Mao, H., Park, J., Sadrosadati, M., & Mutlu, O. (2025) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1145/3695053.3731116 · Cited by 16 · see citing works
“To identify the most relevant data, RAG employs dense retrieval [83, 335], a similarity search operation on dense vectors representing the semantics of the text, called embed-dings [20, 158, 160, 164, 202, 211, 292, 293].”
Enhancing Contextual Understanding of Mistral LLM with External Knowledge BasesPreprint
Sasaki, M., Watanabe, N., & Komanaka, T. (2024) · Research Square · doi:10.21203/rs.3.rs-4215447/v1 · Cited by 16 · see citing works
TOME: A Two-stage Approach for Model-based Retrieval
Ren, R., Zhao, W. X., Liu, J., Wu, H., Wen, J.-R., & Wang, H. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.336 · Cited by 14 · see citing works
Self-citationLegal AI in Low-Resource Languages: Building and Evaluating QA Systems for the Kazakh Legislation
Rakhimova, D., Turarbek, A., Karyukin, V., Sarsenbayeva, A., & Alieyev, R. (2025) · Computers · doi:10.3390/computers14090354 · Cited by 15 · see citing works
Huangpu, Q., & Gao, H. (2024) · doi:10.31219/osf.io/hax36 · Cited by 13 · see citing works
Kim, J. H., & Kim, H. R. (2024) · Research Square · doi:10.21203/rs.3.rs-4328966/v1 · Cited by 13 · see citing works
Embedding-Based Music Emotion Recognition Using Composite Loss
Takashima, N., Li, F., Grzegorzek, M., & Shirahama, K. (2023) · IEEE Access · doi:10.1109/access.2023.3265807 · Cited by 11 · see citing works
“We use the Mean Reciprocal Rank (MRR) as the main evaluation metric as it is commonly employed in retrieval studies [11], [12], [54].”
MethodSalmi, S., Mérelle, S. Y. M., van Eijk, N. L., Gilissen, R., van der Mei, R., & Bhulai, S. (2024) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2024.105760 · Cited by 11 · see citing works
Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation
Shi, T., Xu, J., Zhang, X., Zang, X., Zheng, K., Song, Y., & Li, H. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730075 · Cited by 15 · see citing works
Large Language Model in Materials Science: Roles, Challenges, and Strategic Outlook
Zhang, J., Chen, X., Ye, X., Yang, Y., & Ai, B. (2025) · Advanced Intelligent Discovery · doi:10.1002/aidi.202500085 · Cited by 15 · see citing works
Crop GraphRAG: pest and disease knowledge base Q&A system for sustainable crop protection
Wu, H., Xie, N., Wang, X., Fan, J., Li, Y., & Meng, Z. (2026) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1696872 · Cited by 10 · see citing works
“Given a user question q , an encoder maps it to a query vector v q = Encoder( q ), where v q ∈ R d denotes a dense d -dimensional representation (Zhao et al., 2024).”
Hou, J., Cosma, G., & Finke, A. (2024) · Information Sciences · doi:10.1016/j.ins.2024.121368 · Cited by 10 · see citing works
CAME: Competitively Learning a Mixture-of-Experts Model for First-stage Retrieval
Guo, J., Cai, Y., Bi, K., Fan, Y., Chen, W., Zhang, R., & Cheng, X. (2024) · ACM Transactions on Information Systems · doi:10.1145/3678880 · Cited by 11 · see citing works
“In addition, given the practical needs in product search, where the data comes from different domains, search scenarios, or product categories, the MoE framework is employed in various e-commerce platforms [41, 53].”
Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks
Guo, Z., Cheng, S., Wang, Y., Li, P., & Liu, Y. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.693 · Cited by 15 · see citing works
Understanding and Mitigating the Threat of Vec2Text to Dense Retrieval Systems
Zhuang, S., Koopman, B., Chu, X., & Zuccon, G. (2024) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3673791.3698414 · Cited by 12 · see citing works
“These retrievers utilize text embedding models to encode both queries and documents into embeddings.”
Self-Calibrated Listwise Reranking with Large Language Models
Ren, R., Wang, Y., Zhou, K., Zhao, W. X., Wang, W., Liu, J., Wen, J.-R., & Chua, T. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714658 · Cited by 12 · see citing works
“Text reranking is a fundamental task in the information retrieval (IR) area focusing on scoring and reranking a set of retrieved text candidates ( e.g., passages and documents) on the input query [38].”
Self-citationCG-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 12 · see citing works
Kamalipour, A. A., Asadi, S., & Chimeh, M. M. A. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.100925 · Cited by 12 · see citing works
Injecting the score of the first-stage retriever as text improves BERT-based re-rankers
Askari, A., Abolghasemi, A., Pasi, G., Kraaij, W., & Verberne, S. (2024) · Discover Computing · doi:10.1007/s10791-024-09435-8 · Cited by 10 · see citing works
“Knowledge distillation methods can be categorized into methods that employ multiple teachers of one type of model, called teacher ensembles, or methods that use different types of models as teachers [75].”
Decomposing Complex Queries for Tip-of-the-tongue Retrieval
Lin, K., Lo, K., Gonzalez, J. E., & Klein, D. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.367 · Cited by 14 · see citing works
BiG: A bidirectional group-wise contrastive learning method for multi-label text classification
Xiong, J., Yu, L., & Niu, X. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127977 · Cited by 8 · see citing works
Multi-hop Evidence Retrieval for Cross-document Relation Extraction
Lu, K., Hsu, I.-H., Zhou, W., Ma, M. D., & Chen, M. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.657 · Cited by 8 · see citing works
The Web Can Be Your Oyster for Improving Language Models
Li, J., Tang, T., Zhao, W. X., Wang, J., Nie, J., & Wen, J.-R. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.46 · Cited by 8 · see citing works
Self-citationCorpus Subsampling: Estimating the Effectiveness of Neural Retrieval Models on Large Corpora
Fröbe, M., Parry, A., Scells, H., Wang, S., Zhuang, S., Zuccon, G., Potthast, M., & Hagen, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88708-6_29 · Cited by 7 · see citing works
“Encoding the corpus would be an unrealistic expense for validation [77], especially as often only one relevant document is available per query [76].”
Robust 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 14 · see citing works
He, J., Zhang, B., Rouhizadeh, H., Chen, Y., Yang, R., Lu, J. S., Chen, X., Liu, N., & Teodoro, D. (2026) · Artificial Intelligence Review · doi:10.21203/rs.3.rs-8330917/v1 · Cited by 17 · see citing works
Large Language Models and Recommendation Systems: A Proof-of-Concept Study on Public Procurements
Nai, R., Sulis, E., Fatima, I., & Meo, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70242-6_27 · Cited by 7 · see citing works
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 13 · see citing works
Self-citationChen, 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 6 · see citing works
Collaborative Knowledge Fusion: A Novel Method for Multi-Task Recommender Systems via LLMs
Zhao, C., Su, X., He, M. X., Zhao, H., Jianping Fan, B., & Li, X. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3581706 · Cited by 6 · see citing works
“On the other hand, this extended multi-task approach can also serve as a regularization mechanism [2], helping to prevent the model from overfitting.”
InfluentialRAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation
Cheng, S., Li, J., Wang, H., & Ma, Y. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747741 · Cited by 7 · see citing works
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 7 · see citing works
Hybrid Inverted Index Is a Robust Accelerator for Dense Retrieval
Zhang, P., Liu, Z., Xiao, S., Dou, Z., & Yao, J. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.116 · Cited by 6 · see citing works
“…has become the de-facto paradigm for high-quality first-stage text retrieval, serving as a fundamental component in various information access applications such as search engines (Zou et al., 2021), recommender systems (Zhao et al., 2022), and question answering systems (Karpukhin et al., 2020).”
BackgroundWang, H., Guo, B., Zeng, Y., Chen, M., Ding, Y., Zhang, Y., Yao, L., & Yu, Z. (2025) · ACM Transactions on Information Systems · doi:10.1145/3715098 · Cited by 6 · see citing works
Complex QA and language models hybrid architectures, SurveyPreprint
Daull, X., Bellot, P., Bruno, E., Martin, V., & Murisasco, É. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.09051 · Cited by 17 · see citing works
Sparse-Guided Partial Dense for Cross-Modal Remote Sensing Image–Text Retrieval
Zhao, Z., Miao, X., Liu, L., Xu, X., Liu, Y., Hu, J., Min, B., Gao, Y., & Pharksuwan, K. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3555956 · Cited by 6 · see citing works
“Dense and sparse retrieval paradigms have been extensively studied and applied in single-modal text retrieval tasks [14], [15], [16].”
Ye, Z., Qi, D., Liu, H., & Zhang, S. (2025) · Electronics · doi:10.3390/electronics14163284 · Cited by 5 · see citing works
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 5 · see citing works
“In a common multi-stage search pipeline [53], encompassing both a retriever and a reranker, the goal of retriever is to efficiently fetch 𝑘 candidate datasets based on a relevance metric Rel ( 𝑄,𝐷 ) for each 𝐷 ∈ D .”
Dense Re-Ranking with Weak Supervision for RDF Dataset Search
Chen, Q., Huang, Z., Zhang, Z., Luo, W., Lin, T., Shi, Q., & Cheng, G. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47240-4_2 · Cited by 5 · see citing works
Meng, C., Tang, C. C., Todo, Y., & Ding, W. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113964 · Cited by 4 · see citing works
REJEPA: A Novel Joint-Embedding Predictive Architecture for Efficient Remote Sensing Image Retrieval
Choudhury, S., Salunkhe, Y., Mehrotra, S., & Banerjee, B. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00223 · Cited by 4 · see citing works
“Deep learning (DL)-based methods have become the cornerstone of CBIR, with self-supervised learning (SSL) emerging as a promising approach due to its ability to learn meaningful representations without the need for costly manual annotations [32, 40].”
Cross-modal Representation Shift Refinement for Point-supervised Video Moment Retrieval
Wang, K., Hu, Y., Liu, H., Shao, J., & Nie, L. (2025) · ACM Transactions on Information Systems · doi:10.1145/3786606 · Cited by 4 · see citing works
Chang, S., Ahn, G.-J., & Park, S. (2024) · IEEE Access · doi:10.1109/access.2024.3382190 · Cited by 4 · see citing works
“The pipeline of an information retrieval model (modified from [36]). per headlines [10], etc., are used as pseudo-queries to replace queries related to the searched documents.”
MethodZhang, W., Huang, J.-H., Vakulenko, S., Xu, Y., Rajapakse, T. C., & Kanoulas, E. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78495-8_6 · Cited by 5 · see citing works
CPWS: Confident Programmatic Weak Supervision for High-Quality Data Labeling
Ruan, S., Liu, H., Chen, Z., Feng, B., Zhang, K., Cao, C. C., Chen, E., & Chen, L. (2025) · ACM Transactions on Information Systems · doi:10.1145/3725730 · Cited by 4 · see citing works
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 7 · see citing works
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 5 · see citing works
Some Like It Small: Czech Semantic Embedding Models for Industry Applications
Bednář, J., Náplava, J., Baranċíková, P., & Lisický, O. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i21.30307 · Cited by 4 · see citing works
Dong, Z., Tang, T., Li, J., Zhao, W. X., & Wen, J.-R. (2023) · arXiv · doi:10.48550/arxiv.2309.13345 · Cited by 7 · see citing works
“Previous work has attempted to employ these techniques to solve long text tasks with pretrained language models (Gong et al., 2020; Zhang et al., 2022; Zhao et al., 2022).”
MethodSelf-citationThe Search for Stability: Learning Dynamics of Strategic Publishers with Initial Documents
Madmon, O., Pipano, I., Reinman, I., & Tennenholtz, M. (2025) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.17997 · Cited by 3 · see citing works
“4 In our model, the information need is represented in the same embedding space as the documents, inspired by BERT rankers and dense retrieval models [36, 45, 46].”
Knowledge-augmented large language model-based framework for adverse drug reaction analysis
Zou, H., Wang, Y., Xiang, K., & Huang, A. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.114025 · Cited by 3 · see citing works
Multi-model pseudo-document generation and reconstruction for hybrid query expansion
Wu, Y., & Wang, K. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104543 · Cited by 3 · see citing works
Early-stage architecture design assistance by LLMs and knowledge graphs
Li, D., Shi, Y., Schwartz, M., & Kapadia, M. (2026) · Automation in Construction · doi:10.1016/j.autcon.2025.106756 · Cited by 3 · see citing works
Menad, S., Abdeddaïm, S., & Soualmia, L. F. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42935-4_3 · Cited by 3 · see citing works
Maryamah, M., Wilsen, G., Suhalim, C. T., Septiana, R., Fajar, A., & Solihin, M. I. (2024) · International Conference on Knowledge and Smart Technology · doi:10.1109/kst61284.2024.10499674 · Cited by 6 · see citing works
It's About Time: Incorporating Temporality in Retrieval Augmented Language Models
Gade, A., Jetcheva, J. G., & Trivedi, H. (2025) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai64502.2025.00019 · Cited by 3 · see citing works
“An aspect of question answering that has emerged as a challenge for both RALMs and LLMs are questions whose answers evolve over over time as seen in [17].”
R 2 LLMs: Retrieval and Ranking with LLMs
Zuccon, G., Zhuang, S., & Ma, X. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3731689 · Cited by 4 · see citing works
Comprehending C codes with LLMs: Effective comment generation through retrieval and reasoning
Majumdar, S., Deshpande, A., Das, P. P., & Chakrabarti, P. P. (2025) · Pattern Recognition Letters · doi:10.1016/j.patrec.2025.10.007 · Cited by 4 · see citing works
Enhancing the RAG Pipeline Through Advanced Optimization Techniques
Ilyas, Q. M., & Aziz, S. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-6255-6.ch003 · Cited by 2 · see citing works
Query Performance Prediction Using Dimension Importance Estimators
Faggioli, G., Ferro, N., Perego, R., & Tonellotto, N. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88711-6_13 · Cited by 2 · see citing works
LIST: learning to index spatio-textual data for embedding based spatial keyword queries
Yin, Z., Feng, S., Liu, S., Cong, G., Ong, Y.-S., & Cui, B. (2025) · The VLDB Journal · doi:10.1007/s00778-024-00886-5 · Cited by 2 · see citing works
“Graph-based algorithms like Hierarchical Navigable Small World (HNSW) index [52] construct proximity graphs and perform a beam search on the graph for a given query to find similar embeddings.”
CoDIME: A Counterfactual Approach for Dimension Importance Estimation through Click Logs
Faggioli, G., Ferro, N., Perego, R., & Tonellotto, N. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3729926 · Cited by 3 · see citing works
Projection-Displacement-Based Query Performance Prediction for Embedded Space of Dense Retrievers
Datta, S., Faggioli, G., Ferro, N., Ganguly, D., Muntean, C. I., Perego, R., & Tonellotto, N. (2025) · ACM Transactions on Information Systems · doi:10.1145/3765617 · Cited by 3 · see citing works
“We now describe our proposed methodology of projection-based QPP estimation.”
Learning to rank under uncertainty: a robust neural approach
Khodabakhsh, M., & Ebrahim Bagheri, A. (2025) · Knowledge and Information Systems · doi:10.1007/s10115-025-02601-4 · Cited by 2 · see citing works
Tian, L., & Ma, J. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11254888 · Cited by 2 · see citing works
“Tools such as FAISS provide efficient vector retrieval acceleration, demonstrating strong performance in question-answering systems and recommendation tasks [12], [13].”
Evaluating Lexical, Dense, and Hybrid Retrieval Pipelines for RAG
Abirami, S., Joshma, M. J., Jayavarthini, A., Joshi, A., & Gajendran, M. K. (2025) · IEEE Pune Section International Conference (PuneCon) · doi:10.1109/punecon67554.2025.11379254 · Cited by 2 · see citing works
“…in a single extensible pipeline and reporting both what is recovered and what it costs, our study offers a practical map of the lexical–dense–hybrid design space for RAG and a foundation for future research on retrieval architectures, fusion, and adaptive routing [3], [9], [11], [13]– [15].”
Anchored dense-chain pseudo-relevance feedback: sequential state refinement for neural retrieval
Albishre, K. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00604-x · Cited by 2 · see citing works
“Small changes to the query embedding can result in substantial changes to nearest-neighbor rankings (Zhao et al. 2024).”
SJORS: A Semantic Recommender System for Journalists
Garrido, Á. L., Pera, M. S., & Bobed, C. (2023) · Business & Information Systems Engineering · doi:10.1007/s12599-023-00843-6 · Cited by 2 · see citing works
“In this context, some dense retrieval techniques could be explored (Zhao et al. 2022), although they suffer from the update problem as well.”
Context-Aware Search for Environmental Data Using Dense Retrieval
Wetzel, S., & Mäs, S. (2024) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi13110380 · Cited by 2 · see citing works
Refined Medical Search via Dense Retrieval and User Interaction
Goli, R., Moffat, A., & Buchanan, G. R. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730292 · Cited by 2 · see citing works
“Dense retrieval models are commonly built on top of a general-purpose language model constructed from a large-scale non-specific corpus, and then fine-tuned for a specific retrieval task [34].”
ProActLLM: Proactive Conversational Information Seeking with Large Language Models
Chatterjee, S., Wang, X., Zhang, S., Ebrahimi, S., Ren, Z., Ganguly, D., Jones, G. J. F., Yılmaz, E., & Zamani, H. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761593 · Cited by 2 · see citing works
A Dense Retrieval System and Evaluation Dataset for Scientific Computational Notebooks
Li, N., Zhang, Y., & Zhao, Z. (2023) · IEEE International Conference on eScience · doi:10.1109/e-science58273.2023.10254859 · Cited by 2 · see citing works
Improving Human Resources’ Efficiency with a Generative AI-Based Resume Analysis Solution
Tran, T. T., Nguyen, T. G., Dang, T. H., & Yoshinaga, Y. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-8296-7_25 · Cited by 2 · see citing works
Oussaidene, S., Lhadj, L. S., & Boughanem, M. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0579-8_4 · Cited by 1 · see citing works
Hierarchical Indexing for Interactive Zooming of Document Clusters
Saadeh, H., & Tekli, J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0579-8_21 · Cited by 1 · see citing works
: A Voting-Based Paradigm for Enhancing Retrieval Augmented Generation
Guan, W., Li, X., Lu, J., & Zhou, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78119-3_9 · Cited by 1 · see citing works
Wang, F., Shi, X., Wang, D., & Lou, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3545430 · Cited by 2 · see citing works
“As the technical progress of neural networks in NLP tasks, dense way is proposed to map a query and the candidate into a high-dimensional space for semantic matching [7], [8].”
Huang, Z., Jia, X., Chen, T., & Zhang, Z. (2025) · Data Intelligence · doi:10.3724/2096-7004.di.2025.0006 · Cited by 1 · see citing works
RIAND: Robustness-Improved and Accelerated Neural-Deduplication
Chen, B. (2025) · IEEE Symposium on Computational Intelligence in Natural Language Processing and Social Media (CI-NLPSoMe) · doi:10.1109/ci-nlpsome64976.2025.10970772 · Cited by 1 · see citing works
“Inspired by previous research in text-retrieval [21], they have the Bi-Encoder and Re-Ranker version provided, which are also used in this study. b) SemDeDup [7]: embeds each text directly and conducts clustering over whole corpora.”
External Retrievals or Internal Priors? From RAG to Epitome-Augmented Generation by Fuzzy Selection
He, K., Xu, J., Lin, Q., Wang, W., Gao, Z., Wu, J., Huang, Y., & Feng, M. (2025) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2025.3581205 · Cited by 1 · see citing works
“This approach assumes that every question requires the same amount of relevant information [26].”
- Authors
- Zhao, W. X., Liu, J., Ren, R., & Wen, J.-R.
- Affiliations
- Renmin University of China (CN)
- Baidu (China) (CN)
- Venue
- ACM Transactions on Information Systems
- Published
- 2024-02-09
- Volume
- 42
- Issue
- 4
- Pages
- 1-60
- ISSN
- 1046-8188 (ISSN-L)
- 1558-2868
- OpenAlex
- W4389921502
- Cited by
- 211
- References
- 156
- Citations by year
- 2026: 72 · 2025: 79 · 2024: 40 · 2023: 20
- FWCI
- 49.52
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM Transactions on Information Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62222215, and U2001212)
- Beijing Natural Science Foundation (4222027)
- 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
- pre-trained language models, semantic matching, relevance modeling, text representation learning
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
