mlsanityData to 7 Oct 2026

Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict

arXiv 2605.14473 ↗First posted 14 May 2026cs.CL cs.AIcited by 15

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) is usually evaluated by whether the final answer is correct. Under knowledge conflict, this hides a key question: did the model follow retrieved evidence, rely on its parametric prior, or produce a post-hoc rationale? We study this as context compliance, the regime in which retrieved context controls the answer even when it conflicts with the model's prior knowledge. We introduce Context-Driven Decomposition (CDD), an inference-time diagnostic intervention that elicits contextual and prior answers, isolates the conflicting premise, and records a resolution trace that can be perturbed. Across Epi-Scale stress tests, TruthfulQA misconception injection, and cross-model reruns, CDD makes three behaviors visible. First, misleading retrieval can severely degrade accuracy: under a worst-case TruthfulQA misconception-injection probe, Standard RAG reaches only 15.0%. Second, better answers need not share the same mechanism: CDD improves adversarial accuracy on Gemini-2.5-Flash and shows directional gains across Claude variants, yet trace-perturbation sensitivity is high only on Gemini. Third, explicit decomposition improves controlled-conflict robustness over a conflict-aware instruction baseline on localized factual conflicts, with the clearest margins on Entity Swap (88.0% vs 79.3%) and Logical Contradiction (83.2% vs 75.4%). We frame RAG conflict handling as an observability problem.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 25 of its 42 references that are in the map. First posted on arXiv 14 May 2026.

Builds on

25 of 42 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models9 Oct
  2. 2024ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence16 Apr
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 22

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  6. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  7. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  8. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  9. 2023Large Language Modelscited by 774
  10. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  11. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
  12. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
10 more
  1. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 349
  2. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 333
  3. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 319
  4. 2024Knowledge Conflicts for LLMs: A Surveycited by 274
  5. 2024PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Modelscited by 251
  6. 2024Corrective Retrieval Augmented Generationcited by 187
  7. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 142
  8. 2026Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysiscited by 20
  9. 2026Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-offcited by 13
  10. 2025DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoningcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 15.

15 papers.

Sort:

By area:

  1. 2026Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidancecited by 12
  2. 2026Beyond Accuracy: Measuring Bias Acknowledgment in Chain-of-Thought Reasoning for Responsible AI Evaluationcited by 8
  3. 2026DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderationcited by 4
  4. 2026When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agentscited by 3
  5. 2026Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Accesscited by 2
  6. 2026Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elitecited by 1
  7. 2026Chains That See, Answers That Don't: A Multi-Aspect Evaluation Recipe for Forced Chain-of-Thought on Video-MMEcited by 1
  8. 2026Auditing the Audit: Five Failure Modes in Benchmark-Validity Auditscited by 1
  9. 2026Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQLcited by 1
  10. 2026MOSAIC: Orchestrating Collaborative Knowledge Tracing with Hierarchical Semantic Alignmentcited by 0
  11. 2026Probe Choice Changes Canary-Memorization Verdicts: Three Post-Hoc Disagreement Case Studies in a Text-Dominant LoRA-Tuned Autoregressive Testbedcited by 0
  12. 2026Governing Generative AI Across Financial Institutions: A Framework for Generative AI Risk Controlcited by 0
3 more
  1. 2026Exploratory As-Analyzed No-Detection of Culturally-Marked Predicate-Triggered PII Amplification in a Synthetic-English RAG Probe: A Predicate-Resource-Confounded Auditcited by 0
  2. 2026The Civilization Framework: Sovereign-Anchored Communication Between Personal Multi-Agent Systemscited by 0
  3. 2026Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answerscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation
  2. 2025Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation
  3. 2026When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG
  4. 2026Evaluating RAG Reliability under Clean, Misleading, and Mixed Retrieval
  5. 2026Prompt-Based Abstention Fails Under Misleading Context: A Controlled Study of Small Frozen RAG Models
  6. 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
  7. 2025Rethinking All Evidence: Enhancing Trustworthy Retrieval-Augmented Generation via Conflict-Driven Summarization
  8. 2026Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG