mlsanityData to 7 Oct 2026

Hallucination detection in RAG

74 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: hallucination, hallucinations, detection, hallucination detection, rag

Key facts. Hallucination detection in RAG: 74 papers on arXiv since 2023 (data through 7 Oct 2026). 34 of its 74 mapped papers (46%) cite “RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models” (2023, arXiv 2401.00396). 12 of its 74 mapped papers (16%) cite “ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability” (2024, arXiv 2410.11414). 2 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

2 new since 17 Sep

  1. Grounding Probes: Generator-Independent Hallucination Detection from Observer Model Hidden States
  2. RAGScope: A Leakage-Controlled, Cost-Aware Evidence-Gating Protocol for RAG Hallucination Triage also fits: Privacy and security of RAG

Foundations

Most cited by papers here

  1. RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models2023cited by 34 here
  2. ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability2024cited by 12 here
  3. LettuceDetect: A Hallucination Detection Framework for RAG Applications2025cited by 7 here
  4. LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation2024cited by 6 here
  5. Lynx: An Open Source Hallucination Evaluation Model2024cited by 5 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 9 here
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 49 here
  3. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 4 here
  4. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 5 here
  5. 2023Active Retrieval Augmented Generationcited by 3 here
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 14 here
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 15 here
  8. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 5 here
  9. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretabilitycited by 12 here
15 more it builds on, not in this chain
  1. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 9 here
  2. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 7 here
  3. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 4 here
  4. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 10 here
  5. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 6 here
  6. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 34 here
  7. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 3 here
  8. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 12 here
  9. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 4 here
  10. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoningcited by 3 here
  11. 2024RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systemscited by 5 here
  12. 2024Lynx: An Open Source Hallucination Evaluation Modelcited by 5 here
  13. 2024LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagationcited by 6 here
  14. 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"cited by 4 here
  15. 2025LettuceDetect: A Hallucination Detection Framework for RAG Applicationscited by 7 here

The 24 most cited of 149.

Browse

30 of 74, ranked 6–35

  1. 6Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards20253
  2. 7LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals20253
  3. 8SEReDeEP: Hallucination Detection in Retrieval-Augmented Models via Semantic Entropy and Context-Parameter Fusion20252
  4. 9HalluSearch at SemEval-2025 Task 3: A Search-Enhanced RAG Pipeline for Hallucination Detection20251
  5. 10Removal of Hallucination on Hallucination: Debate-Augmented RAG20251
  6. 11Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMs20251
  7. 12HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation20251
  8. 13InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generation20251
  9. 14Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment20251
  10. 15Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics20241
All 30
  1. 16Reducing hallucination in structured outputs via Retrieval-Augmented Generation20241
  2. 17RAL2M: Retrieval Augmented Learning-To-Match Against Hallucination in Compliance-Guaranteed Service Systems20260
  3. 18Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation20260
  4. 19Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph20260
  5. 20Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Survey20260
  6. 21INTRYGUE: Induction-Aware Entropy Gating for Reliable RAG Uncertainty Estimation20260
  7. 22MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination20260
  8. 23Mitigating Hallucination on Hallucination in RAG via Ensemble Voting20260
  9. 24Retromorphic Testing with Hierarchical Verification for Hallucination Detection in RAG20260
  10. 25LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment20260
  11. 26From Binary Groundedness to Support Relations: Towards a Reader-Centred Taxonomy for Comprehension of AI Output20260
  12. 27RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration20260
  13. 28HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models20260
  14. 29K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Finance20260
  15. 30Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation20260
  16. 31Evidence Graph Consistency in Retrieval-Augmented Generation: A Model-Dependent Analysis of Hallucination Detection20260
  17. 32Mitigating Visual Hallucinations in Multimodal Systems through Retrieval-Augmented Reliability-Aware Inference20260
  18. 33MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation20260
  19. 34CORTEX: Token-Level Hallucination Detection in RAG via Comparative Internal Representations20260
  20. 35Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents20260