mlsanityData to 14 Oct 2026

InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generation

arXiv 2510.21538 ↗First posted 24 Oct 2025cs.CLcited by 1

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) integrates external knowledge to mitigate hallucinations, yet models often generate outputs inconsistent with retrieved content. Accurate hallucination detection requires disentangling the contributions of external context and parametric knowledge, which prior methods typically conflate. We investigate the mechanisms underlying RAG hallucinations and find they arise when later-layer FFN modules disproportionately inject parametric knowledge into the residual stream. To address this, we explore a mechanistic detection approach based on external context scores and parametric knowledge scores. Using Qwen3-0.6b, we compute these scores across layers and attention heads and train regression-based classifiers to predict hallucinations. Our method is evaluated against state-of-the-art LLMs (GPT-5, GPT-4.1) and detection baselines (RAGAS, TruLens, RefChecker). Furthermore, classifiers trained on Qwen3-0.6b signals generalize to GPT-4.1-mini responses, demonstrating the potential of proxy-model evaluation. Our results highlight mechanistic signals as efficient, generalizable predictors for hallucination detection in RAG systems.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation. Builds on 19 of its 25 references that are in the map. First posted on arXiv 24 Oct 2025.

Builds on

19 of 25 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025HalluSearch at SemEval-2025 Task 3: A Search-Enhanced RAG Pipeline for Hallucination Detection14 Apr
  2. 2025LettuceDetect: A Hallucination Detection Framework for RAG Applications24 Feb
  3. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability15 Oct
  4. 2024LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation28 Aug
  5. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models31 Dec

Other references · 14

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  3. 2024A Survey on Large Language Models for Code Generationcited by 658
  4. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 418
  5. 2024RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systemscited by 117
  6. 2023Neuron-Level Knowledge Attribution in Large Language Modelscited by 37
  7. 2025SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakescited by 27
  8. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Surveycited by 20
  9. 2024Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Modelscited by 15
  10. 2024InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Modelscited by 13
  11. 2024Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysiscited by 7
  12. 2025FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Modelscited by 6
2 more
  1. 2024Large Language Models for Code Summarizationcited by 3
  2. 2025MechIR: A Mechanistic Interpretability Framework for Information Retrievalcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026INTRYGUE: Induction-Aware Entropy Gating for Reliable RAG Uncertainty Estimationcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
  2. 2026RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration
  3. 2026Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph
  4. 2025SEReDeEP: Hallucination Detection in Retrieval-Augmented Models via Semantic Entropy and Context-Parameter Fusion
  5. 2025The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems
  6. 2025Osiris: A Lightweight Open-Source Hallucination Detection System
  7. 2025TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG
  8. 2024Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs