mlsanityData to 7 Oct 2026

Dense Text Retrieval based on Pretrained Language Models: A Survey

arXiv 2211.14876 ↗First posted 27 Nov 2022cs.IRcited by 136

Not on the map. Why?

Cited by 39 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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 classic 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 the text representation and model the relevance matching. The recent success of pretrained language models (PLMs) 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 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 referred to as dense retrieval, since it employs dense vectors (a.k.a., embeddings) to represent the texts. Considering the rapid progress on dense retrieval, in this survey, we systematically review the recent advances on PLM-based dense retrieval. Different from previous surveys on dense retrieval, we take a new perspective to organize the related work by four major aspects, including architecture, training, indexing and integration, and summarize the mainstream techniques for each aspect. We thoroughly survey the literature, and include 300+ related reference papers on dense retrieval. To support our survey, we create a website for providing useful resources, and release a code repertory and toolkit for implementing dense retrieval models. This survey aims to provide a comprehensive, practical reference focused on the major progress for dense text retrieval.

Key facts. Cited by 136 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Nov 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 22; 2024: 48; 2025: 51; 2026: 12.

136 papers.

Sort:

By area:

  1. 2023A Survey of Large Language Modelscited by 2,537
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  3. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  4. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  5. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  6. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  7. 2024mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrievalcited by 233
  8. 2024GME: Improving Universal Multimodal Retrieval by Multimodal LLMscited by 166
  9. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learningcited by 152
  10. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  11. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 122
  12. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Modelscited by 77
38 more
  1. 2024Reliable, Adaptable, and Attributable Language Models with Retrievalcited by 73
  2. 2024When Search Engine Services meet Large Language Models: Visions and Challengescited by 59
  3. 2023BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Modelscited by 53
  4. 2023Neural Retrievers are Biased Towards LLM-Generated Contentcited by 37
  5. 2024The Chronicles of RAG: The Retriever, the Chunk and the Generatorcited by 34
  6. 2023Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Methodcited by 29
  7. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Surveycited by 29
  8. 2024REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answeringcited by 28
  9. 2023Large Language Models are Built-in Autoregressive Search Enginescited by 26
  10. 2024Towards Completeness-Oriented Tool Retrieval for Large Language Modelscited by 26
  11. 2023Decomposing Complex Queries for Tip-of-the-tongue Retrievalcited by 24
  12. 2024BASES: Large-scale Web Search User Simulation with Large Language Model based Agentscited by 24
  13. 2025Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generationcited by 23
  14. 2025Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generationcited by 23
  15. 2023Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Taskscited by 21
  16. 2024Corpus Poisoning via Approximate Greedy Gradient Descentcited by 21
  17. 2023Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinesecited by 18
  18. 2023AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrievalcited by 18
  19. 2024Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integrationcited by 17
  20. 2024Enhancing Tool Retrieval with Iterative Feedback from Large Language Modelscited by 17
  21. 2025An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunitiescited by 17
  22. 2024Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspectivecited by 15
  23. 2025O1 Embedder: Let Retrievers Think Before Actioncited by 15
  24. 2024PIRB: A Comprehensive Benchmark of Polish Dense and Hybrid Text Retrieval Methodscited by 14
  25. 2024Self-Cognition in Large Language Models: An Exploratory Studycited by 14
  26. 2024Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answeringcited by 14
  27. 2024On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domainscited by 14
  28. 2022Multi-hop Evidence Retrieval for Cross-document Relation Extractioncited by 13
  29. 2024Dense Passage Retrieval: Is it Retrieving?cited by 12
  30. 2023Language Models are Universal Embedderscited by 11
  31. 2024Generative Dense Retrieval: Memory Can Be a Burdencited by 11
  32. 2024Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracingcited by 11
  33. 2025Interpersonal Memory Matters: A New Task for Proactive Dialogue Utilizing Conversational Historycited by 10
  34. 2025X-GridAgent: An LLM-Powered Agentic AI System for Assisting Power Grid Analysiscited by 10
  35. 2024Understanding and Mitigating the Threat of Vec2Text to Dense Retrieval Systemscited by 9
  36. 2024CorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Taskscited by 9
  37. 2024No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Userscited by 9
  38. 2024Length-Induced Embedding Collapse in PLM-based Modelscited by 9

50 most cited of 136 All 136 (JSON)