mlsanityData to 14 Oct 2026

Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models

arXiv 2410.07176 ↗First posted 9 Oct 2024cs.CL cs.AI cs.LGcited by 58

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval augmented generation (RAG), while effectively integrating external knowledge to address the inherent limitations of large language models (LLMs), can be hindered by imperfect retrieval that contain irrelevant, misleading, or even malicious information. Previous studies have rarely connected the behavior of RAG through joint analysis, particularly regarding error propagation coming from imperfect retrieval and potential conflicts between LLMs' internal knowledge and external sources. Through comprehensive and controlled analyses under realistic conditions, we find that imperfect retrieval augmentation is inevitable, common, and harmful. We identify the knowledge conflicts between LLM-internal and external knowledge from retrieval as a bottleneck to overcome imperfect retrieval in the post-retrieval stage of RAG. To address this, we propose Astute RAG, a novel RAG approach designed to be resilient to imperfect retrieval augmentation. It adaptively elicits essential information from LLMs' internal knowledge, iteratively consolidates internal and external knowledge with source-awareness, and finalizes the answer according to information reliability. Our experiments with Gemini and Claude demonstrate the superior performance of Astute RAG compared to previous robustness-enhanced RAG approaches. Specifically, Astute RAG is the only RAG method that achieves performance comparable to or even surpassing conventional use of LLMs under the worst-case scenario. Further analysis reveals the effectiveness of Astute RAG in resolving knowledge conflicts, thereby improving the trustworthiness of RAG.

Key facts. Cited by 58 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 40 of its 50 references that are in the map. First posted on arXiv 9 Oct 2024.

Builds on

40 of 50 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training31 May
  2. 2024Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation10 Apr
  3. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  4. 2024Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models22 Feb
  5. 2023Learning to Filter Context for Retrieval-Augmented Generation14 Nov
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct
  7. 2023Benchmarking Large Language Models in Retrieval-Augmented Generation4 Sep

Other references · 33

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  3. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  5. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  6. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  7. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  8. 2023Active Retrieval Augmented Generationcited by 516
  9. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  10. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 356
  11. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 341
  12. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
21 more
  1. 2024Knowledge Conflicts for LLMs: A Surveycited by 283
  2. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  3. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 256
  4. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 234
  5. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213
  6. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  7. 2024Corrective Retrieval Augmented Generationcited by 197
  8. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
  9. 2024BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalcited by 158
  10. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 151
  11. 2023Retrieval meets Long Context Large Language Modelscited by 115
  12. 2022Re2G: Retrieve, Rerank, Generatecited by 102
  13. 2024CRAG -- Comprehensive RAG Benchmarkcited by 97
  14. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 77
  15. 2024CompAct: Compressing Retrieved Documents Actively for Question Answeringcited by 64
  16. 2024Scaling Retrieval-Based Language Models with a Trillion-Token Datastorecited by 56
  17. 2024Enhancing Contextual Understanding in Large Language Models through Contrastive Decodingcited by 49
  18. 2023Merging Generated and Retrieved Knowledge for Open-Domain QAcited by 36
  19. 2024Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Modelscited by 28
  20. 2023A Causal View of Entity Bias in (Large) Language Modelscited by 21
  21. 2024Eureka: Evaluating and Understanding Large Foundation Modelscited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 32; 2026: 23.

58 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  2. 2025Multi-Agent Design: Optimizing Agents with Better Prompts and Topologiescited by 113
  3. 2025Safety at Scale: A Comprehensive Survey of Large Model and Agent Safetycited by 67
  4. 2025Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMscited by 55
  5. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  6. 2025Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Modelscited by 39
  7. 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievalscited by 28
  8. 2024To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contextscited by 25
  9. 2025GraphRAG under Firecited by 24
  10. 2025Benchmarking Poisoning Attacks against Retrieval-Augmented Generationcited by 18
  11. 2025ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Searchcited by 18
  12. 2026Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflictcited by 15
38 more
  1. 2025SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAGcited by 13
  2. 2025Agentic Learner with Grow-and-Refine Multimodal Semantic Memorycited by 13
  3. 2025TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge Graphscited by 12
  4. 2025RARE: Retrieval-Augmented Reasoning Modelingcited by 11
  5. 2025Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcementcited by 11
  6. 2025ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checkingcited by 10
  7. 2025Position: Towards a Responsible LLM-empowered Multi-Agent Systemscited by 8
  8. 2025Automatic Dataset Generation for Knowledge Intensive Question Answering Taskscited by 7
  9. 2025Revealing Perception and Generation Dynamics in LVLMs: Mitigating Hallucinations via Validated Dominance Correctioncited by 7
  10. 2025Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruptioncited by 5
  11. 2025OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learningcited by 4
  12. 2026EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibriumcited by 4
  13. 2025MultiRAG: A Knowledge-guided Framework for Mitigating Hallucination in Multi-source Retrieval Augmented Generationcited by 3
  14. 2025Zero-RAG: Towards Retrieval-Augmented Generation with Zero Redundant Knowledgecited by 3
  15. 2025SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligencecited by 3
  16. 2026Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Modelscited by 3
  17. 2025Evaluating the Retrieval Robustness of Large Language Modelscited by 2
  18. 2025Gaussian mixture models as a proxy for interacting language modelscited by 2
  19. 2025Micro-Act: Mitigating Knowledge Conflict in LLM-based RAG via Actionable Self-Reasoningcited by 2
  20. 2025Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Modelscited by 2
  21. 2025MedAI: Evaluating TxAgent's Therapeutic Agentic Reasoning in the NeurIPS CURE-Bench Competitioncited by 2
  22. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directionscited by 2
  23. 2024Context Awareness Gate For Retrieval Augmented Generationcited by 1
  24. 2025ACoRN: Noise-Robust Abstractive Compression in Retrieval-Augmented Language Modelscited by 1
  25. 2025VERIRAG: A Post-Retrieval Auditing of Scientific Study Summariescited by 1
  26. 2025Incentive-Aligned Multi-Source LLM Summariescited by 1
  27. 2026Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learningcited by 1
  28. 2026When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMscited by 1
  29. 2026Conjecture and Inquiry: Quantifying Software Performance Requirements via Interactive Retrieval-Augmented Preference Elicitationcited by 1
  30. 2026LLM-Oriented Information Retrieval: A Denoising-First Perspectivecited by 1
  31. 2026Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Predictioncited by 1
  32. 2026RADAR: Defending RAG Dynamically against Retrieval Corruptioncited by 1
  33. 2026The Powerless Noise: How Experimental Settings Shape the Reported Power of Noisecited by 1
  34. 2026Information Discernment in Large Language Modelscited by 1
  35. 2026MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Modelscited by 1
  36. 2026Return or Revise? Learning When Revision Helps Retrieval-Augmented QAcited by 1
  37. 2025Generating Privacy Stories From Software Documentationcited by 0
  38. 2026BiRD: A Bidirectional Ranking Defense Mechanism for Retrieval Augmented Generationcited by 0

50 most cited of 58 All 58 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Survey
  3. 2024RAGGED: Towards Informed Design of Scalable and Stable RAG Systems
  4. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  5. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  6. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  7. 2025RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation
  8. 2024Retrieval-Augmented Generation with Estimation of Source Reliability