ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
Keywords: Retrieval-Augmented Generation Hallucination, Hallucination Detection, Mechanistic Interpretability
TL;DR: We propose ReDeEP for detecting hallucinations in RAG models by decoupling external context and parametric knowledge, and AARF to reduce hallucinations by modulating the contributions of Knowledge FFNs and Copying Heads.
Abstract: 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 retrieved content, RAG models can still produce hallucinations by generating outputs that conflict with the retrieved information. Detecting such hallucinations requires disentangling how Large Language Models (LLMs) balance external and parametric knowledge. Current detection methods often focus on one of these mechanisms or without decoupling their intertwined effects, making accurate detection difficult. In this paper, we investigate the internal mechanisms behind hallucinations in RAG scenarios. We discover hallucinations occur when the **Knowledge FFNs** in LLMs overemphasize parametric knowledge in the residual stream, while **Copying Heads** fail to effectively retain or integrate external knowledge from retrieved content. Based on these findings, we propose **ReDeEP**, a novel method that detects hallucinations by decoupling LLM’s utilization of external context and parametric knowledge. Our experiments show that ReDeEP significantly improves RAG hallucination detection accuracy. Additionally, we introduce AARF, which mitigates hallucinations by modulating the contributions of Knowledge FFNs and Copying Heads.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 3536
Loading