mlsanityData to 7 Oct 2026

DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models

arXiv 2403.10081 ↗First posted 15 Mar 2024cs.CL cs.IRcited by 63

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Dynamic retrieval augmented generation (RAG) paradigm actively decides when and what to retrieve during the text generation process of Large Language Models (LLMs). There are two key elements of this paradigm: identifying the optimal moment to activate the retrieval module (deciding when to retrieve) and crafting the appropriate query once retrieval is triggered (determining what to retrieve). However, current dynamic RAG methods fall short in both aspects. Firstly, the strategies for deciding when to retrieve often rely on static rules. Moreover, the strategies for deciding what to retrieve typically limit themselves to the LLM's most recent sentence or the last few tokens, while the LLM's real-time information needs may span across the entire context. To overcome these limitations, we introduce a new framework, DRAGIN, i.e., Dynamic Retrieval Augmented Generation based on the real-time Information Needs of LLMs. Our framework is specifically designed to make decisions on when and what to retrieve based on the LLM's real-time information needs during the text generation process. We evaluate DRAGIN along with existing methods comprehensively over 4 knowledge-intensive generation datasets. Experimental results show that DRAGIN achieves superior performance on all tasks, demonstrating the effectiveness of our method. We have open-sourced all the code, data, and models in GitHub: https://github.com/oneal2000/DRAGIN/tree/main

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 31 of its 47 references that are in the map. First posted on arXiv 15 Mar 2024.

Builds on

31 of 47 references.

References · 31

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  9. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  11. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  12. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
19 more
  1. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  2. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  3. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  4. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  5. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  6. 2022SGPT: GPT Sentence Embeddings for Semantic Searchcited by 204
  7. 2021Condenser: a Pre-training Architecture for Dense Retrievalcited by 162
  8. 2020Detecting Hallucinated Content in Conditional Neural Sequence Generationcited by 151
  9. 2021A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generationcited by 137
  10. 2020IIRC: A Dataset of Incomplete Information Reading Comprehension Questionscited by 52
  11. 2022Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformercited by 45
  12. 2023Towards Better Web Search Performance: Pre-training, Fine-tuning and Learning to Rankcited by 17
  13. 2023THUIR@COLIEE 2023: Incorporating Structural Knowledge into Pre-trained Language Models for Legal Case Retrievalcited by 16
  14. 2023Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrievalcited by 15
  15. 2023CaseEncoder: A Knowledge-enhanced Pre-trained Model for Legal Case Encodingcited by 14
  16. 2023THUIR2 at NTCIR-16 Session Search (SS) Taskcited by 12
  17. 2023THUIR at WSDM Cup 2023 Task 1: Unbiased Learning to Rankcited by 11
  18. 2023THUIR@COLIEE 2023: More Parameters and Legal Knowledge for Legal Case Entailmentcited by 11
  19. 2023Caseformer: Pre-training for Legal Case Retrieval Based on Inter-Case Distinctionscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 28; 2026: 22.

63 papers.

Sort:

By area:

  1. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurizationcited by 70
  2. 2026Skill Retrieval Augmentation for Agentic AIcited by 41
  3. 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generationcited by 40
  4. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  5. 2024DMQR-RAG: Diverse Multi-Query Rewriting for RAGcited by 26
  6. 2025Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaborationcited by 19
  7. 2024Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perceptioncited by 17
  8. 2025GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generationcited by 17
  9. 2025SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generationcited by 14
  10. 2024CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Controlcited by 13
  11. 2025Stop-RAG: Value-Based Retrieval Control for Iterative RAGcited by 13
  12. 2024LeKUBE: A Legal Knowledge Update BEnchmarkcited by 12
38 more
  1. 2025Query-Level Uncertainty in Large Language Modelscited by 12
  2. 2024Enhancing LLMs for Impression Generation in Radiology Reports through a Multi-Agent Systemcited by 11
  3. 2025Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoningcited by 11
  4. 2024AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoningcited by 10
  5. 2024Improving Factuality with Explicit Working Memorycited by 10
  6. 2025Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalizationcited by 9
  7. 2025HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generationcited by 9
  8. 2025Context-Guided Dynamic Retrieval for Improving Generation Quality in RAG Modelscited by 8
  9. 2025Conversational Search: From Fundamentals to Frontiers in the LLM Eracited by 8
  10. 2026Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trendscited by 8
  11. 2024QUITO: Accelerating Long-Context Reasoning through Query-Guided Context Compressioncited by 7
  12. 2026Adaptive Stopping for Multi-Turn LLM Reasoningcited by 7
  13. 2026To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Callingcited by 7
  14. 2025Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question Answeringcited by 6
  15. 2025Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Controlcited by 6
  16. 2026LLMs Should Express Uncertainty Explicitlycited by 6
  17. 2025Uncertainty Quantification for Retrieval-Augmented Reasoningcited by 5
  18. 2026PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generationcited by 5
  19. 2024A Multi-Source Retrieval Question Answering Framework Based on RAGcited by 4
  20. 2026The Context Gathering Decision Process: A POMDP Framework for Agentic Searchcited by 4
  21. 2025Dynamic and Parametric Retrieval-Augmented Generationcited by 3
  22. 2026Entropy-Tree: Tree-Based Decoding with Entropy-Guided Explorationcited by 3
  23. 2026Skill-RAG: Failure-State-Aware Retrieval Augmentation via Hidden-State Probing and Skill Routingcited by 3
  24. 2026Evaluating Confidence-Gated Retrieval with Matched Trajectory Replaycited by 3
  25. 2025Fast, Slow, and Tool-augmented Thinking for LLMs: A Reviewcited by 2
  26. 2025FidelityGPT: Correcting Decompilation Distortions with Retrieval Augmented Generationcited by 2
  27. 2025Diverse Human Value Alignment for Large Language Models via Ethical Reasoningcited by 2
  28. 2026FedMosaic: Federated Retrieval-Augmented Generation via Parametric Adapterscited by 2
  29. 2024QCG-Rerank: Chunks Graph Rerank with Query Expansion in Retrieval-Augmented LLMs for Tourism Domaincited by 1
  30. 2024A Survey of Query Optimization in Large Language Modelscited by 1
  31. 2025Foundations of GenIRcited by 1
  32. 2025ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generationcited by 1
  33. 2025Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalizationcited by 1
  34. 2025MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systemscited by 1
  35. 2026CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answeringcited by 1
  36. 2026LLM-Oriented Information Retrieval: A Denoising-First Perspectivecited by 1
  37. 2026Not All Tokens Learn Alike: Attention Entropy Reveals Heterogeneous Signals in RL Reasoningcited by 1
  38. 2026Diagnosing and Repairing Factual Errors in RAG under Budget Constraintscited by 1

50 most cited of 63 All 63 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Survey
  2. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  3. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey
  4. 2025Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Bias
  5. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Models
  6. 2024Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks
  7. 2024Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey
  8. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach