Anchoring Entities: Retrieval-Augmented Hallucination Detection

Runsong Jia, Zhen Fang, Mengjia Wu, Jie Lu, Yi Zhang

Keywords: Hallucination Detection, Retrieval-Augmented Generation, Entity Verification, Large Language Models

TL;DR: We propose EAEV, a method utilizing RAG to detect hallucinations by aligning generated entities with retrieved evidence through multi-dimensional verification and counterfactual stability analysis.

Abstract: Hallucination detection is crucial for large language models (LLMs), as hallucinated content creates significant barriers in applications requiring factual accuracy. Current detection methods mainly depend on internal signals like uncertainty and self-consistency checks, using the model's pre-trained knowledge to identify unreliable outputs. However, pre-trained knowledge may become outdated and has coverage limitations, especially for specialized or recent information. To address these limitations, retrieval-augmented generation (RAG) has emerged as a promising solution that grounds model outputs in external evidence. In this paper, we target a critical and practical learning problem RAG-based hallucination detection (RHD), where RAG is employed to enhance hallucination detection by addressing information updating challenges. To address RHD, we propose a novel method Evidence-Aligned Entity Verification (EAEV), which detects entity-level hallucinations by leveraging RAG to align generated entities with retrieved evidence contexts. Specifically, EAEV evaluates entity-evidence alignment through three complementary dimensions and introduces counterfactual stability analysis to ensure robust alignments under evidence perturbations. Experiments across multiple RAG benchmarks demonstrate that EAEV achieves consistent improvements over existing methods with strong generalization capabilities.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 8968