paper-with-me

Papers

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

2026-01-06 · Jianpeng Hu, Yanzeng Li, Jialun Zhong, Wenfa Qi, Lei Zou 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.

📄 PDF Abstract BibTeX arXiv:2601.03052

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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

2024-08-28 · Haichuan Hu, Yuhan Sun, Quanjun Zhang

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…

RAGRetrievalRetrieval-augmented Generation

Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment

2025-12-09 · Shanghao Li, Jinda Han, Yibo Wang, Yuanjie Zhu 외 arxiv

Graph-based Retrieval-Augmented Generation (GraphRAG) enhances Large Language Models (LLMs) by incorporating external knowledge from linearized subgraphs retrieved from knowledge graphs. However, LLMs struggle to interpr…

Knowledge Graphs

ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability

2024-10-15 · Zhongxiang Sun, Xiaoxue Zang, Kai Zheng, Jun Xu 외

Retrieval-Augmented Generation (RAG) models are designed to incorporate external knowledge, reducing hallucinations caused by insufficient parametric (internal) knowledge. However, even with accurate and relevant retriev…

HallucinationRAGRetrievalRetrieval-augmented Generation

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

2025-10-24 · Likun Tan, Kuan-Wei Huang, Joy Shi, Kevin Wu arxiv

Retrieval-Augmented Generation (RAG) integrates external knowledge to mitigate hallucinations, yet models often generate outputs inconsistent with retrieved content. Accurate hallucination detection requires disentanglin…

Who Stole Your Data? A Method for Detecting Unauthorized RAG Theft

2025-10-09 · Peiyang Liu, Ziqiang Cui, Di Liang, Wei Ye arxiv

Retrieval-augmented generation (RAG) enhances Large Language Models (LLMs) by mitigating hallucinations and outdated information issues, yet simultaneously facilitates unauthorized data appropriation at scale. This paper…