mlsanityData to 7 Oct 2026

LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation

arXiv 2408.15533 ↗First posted 28 Aug 2024cs.CL cs.AIcited by 17

On the map: Retrieval-augmented generation → Hallucination detection in RAG

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has become a primary technique for mitigating hallucinations in large language models (LLMs). However, incomplete knowledge extraction and insufficient understanding can still mislead LLMs to produce irrelevant or even contradictory responses, which means hallucinations persist in RAG. In this paper, we propose LRP4RAG, a method based on the Layer-wise Relevance Propagation (LRP) algorithm for detecting hallucinations in RAG. Specifically, we first utilize LRP to compute the relevance between the input and output of the RAG generator. We then apply further extraction and resampling to the relevance matrix. The processed relevance data are input into multiple classifiers to determine whether the output contains hallucinations. To the best of our knowledge, this is the first time that LRP has been used for detecting RAG hallucinations, and extensive experiments demonstrate that LRP4RAG outperforms existing baselines.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation. Builds on 35 of its 57 references that are in the map. First posted on arXiv 28 Aug 2024.

Builds on

35 of 57 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models31 Dec

Other references · 34

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  7. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  8. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  9. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  10. 2022In-context Learning and Induction Headscited by 930
  11. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  12. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 329
22 more
  1. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 318
  2. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 317
  3. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 292
  4. 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 246
  5. 2023Do Large Language Models Know What They Don't Know?cited by 238
  6. 2016Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layerscited by 197
  7. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  8. 2024Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Toolscited by 170
  9. 2024Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantificationcited by 159
  10. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 150
  11. 2023Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Modelscited by 147
  12. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 138
  13. 2023LM-Polygraph: Uncertainty Estimation for Language Modelscited by 130
  14. 2022Natural Language to Code Translation with Executioncited by 122
  15. 2023Enhancing Uncertainty-Based Hallucination Detection with Stronger Focuscited by 98
  16. 2024Information Flow Routes: Automatically Interpreting Language Models at Scalecited by 92
  17. 2021Evaluating Attribution in Dialogue Systems: The BEGIN Benchmarkcited by 75
  18. 2022Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Bettercited by 75
  19. 2023Detecting and Mitigating Hallucinations in Multilingual Summarisationcited by 48
  20. 2022RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Groundingcited by 47
  21. 2023Faithful Low-Resource Data-to-Text Generation through Cycle Trainingcited by 7
  22. 2024Zero-Shot Multi-task Hallucination Detectioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 8.

17 papers.

Sort:

By area:

  1. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  2. 2024ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Modelscited by 28
  3. 2025Out of Style: RAG's Fragility to Linguistic Variationcited by 10
  4. 2024Attention with Dependency Parsing Augmentation for Fine-Grained Attributioncited by 5
  5. 2025Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generationcited by 5
  6. 2025A Survey on AgentOps: Categorization, Challenges, and Future Directionscited by 3
  7. 2025An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answeringcited by 2
  8. 2026Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graphcited by 2
  9. 2026Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attentioncited by 2
  10. 2026Evidence Graph Consistency in Retrieval-Augmented Generation: A Model-Dependent Analysis of Hallucination Detectioncited by 2
  11. 2025InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generationcited by 1
  12. 2026INTRYGUE: Induction-Aware Entropy Gating for Reliable RAG Uncertainty Estimationcited by 1
5 more
  1. 2026RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integrationcited by 1
  2. 2025The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systemscited by 0
  3. 2026HART: Data-Driven Hallucination Attribution and Evidence-Based Tracing for Large Language Modelscited by 0
  4. 2026Agent System Operations: Categorization, Challenges, and Future Directionscited by 0
  5. 2026Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
  2. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
  3. 2025TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG
  4. 2025Probabilistic distances-based hallucination detection in LLMs with RAG
  5. 2024Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
  6. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
  7. 2025Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generation
  8. 2026Mitigating Hallucination on Hallucination in RAG via Ensemble Voting