mlsanityData to 7 Oct 2026

Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph

arXiv 2601.03052 ↗First posted 6 Jan 2026cs.CLcited by 2

On the map: LLM reasoning → Hallucination detection and mitigation

also in 1 more
Abstract (arXiv)

The Retrieval-augmented generation (RAG) system based on Large language model (LLM) has made significant progress. It can effectively reduce factuality hallucinations, but faithfulness hallucinations still exist. Previous methods for detecting faithfulness hallucinations either neglect to capture the models' internal reasoning processes or handle those features coarsely, making it difficult for discriminators to learn. This paper proposes a semantic-level internal reasoning graph-based method for detecting faithfulness hallucination. Specifically, we first extend the layer-wise relevance propagation algorithm from the token level to the semantic level, constructing an internal reasoning graph based on attribution vectors. This provides a more faithful semantic-level representation of dependency. Furthermore, we design a general framework based on a small pre-trained language model to utilize the dependencies in LLM's reasoning for training and hallucination detection, which can dynamically adjust the pass rate of correct samples through a threshold. Experimental results demonstrate that our method achieves better overall performance compared to state-of-the-art baselines on RAGTruth and Dolly-15k.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 17 of its 45 references that are in the map. First posted on arXiv 6 Jan 2026.

Builds on

17 of 45 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models21 Nov
  2. 2025HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation1 Oct

Other references · 15

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  3. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  4. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  5. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 317
  6. 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 246
  7. 2022Rethinking with Retrieval: Faithful Large Language Model Inferencecited by 145
  8. 2024Constructing Benchmarks and Interventions for Combating Hallucinations in LLMscited by 19
  9. 2024LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagationcited by 17
  10. 2025Do LLMs Signal When They're Right? Evidence from Neuron Agreementcited by 10
  11. 2024Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generationcited by 6
  12. 2025Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainabilitycited by 6
3 more
  1. 2025Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Modelscited by 3
  2. 2025Knowing the Facts but Choosing the Shortcut: Understanding How Large Language Models Compare Entitiescited by 2
  3. 2025HalluClean: A Unified Framework to Combat Hallucinations in LLMscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026How Much Do Legal RAG Systems Still Hallucinate?cited by 0
  2. 2026Locating Answer-Correctness Signals in Frozen Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
  2. 2026RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration
  3. 2025InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generation
  4. 2025LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
  5. 2024Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
  6. 2026Unmasking Hallucinations: A Causal Graph-Attention Perspective on Factual Reliability in Large Language Models
  7. 2025The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems
  8. 2025AutoRAG-LoRA: Hallucination-Triggered Knowledge Retuning via Lightweight Adapters