Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads

摘要

Recent progress in large language models (LLMs) has led to systems capable of producing text with remarkable fluency. However, these models are still prone to factual inaccuracies, often referred to as \``hallucinations''. One strategy to alleviate this issue is uncertainty quantification (UQ), but most existing approaches are computationally intensive or require supervision. In this work, we propose Recurrent Attention-based Uncertainty Quantification (RAUQ), an unsupervised and efficient framework for identifying hallucinations. The method leverages an observation about transformer attention behavior: when incorrect information is generated, certain ``uncertainty-aware'' attention heads, tend to reduce their focus on preceding tokens. RAUQ automatically detects these attention heads and combines their activation patterns with token-level confidence measures in a recurrent scheme, producing a sequence-level uncertainty estimate in just a single forward pass. Through experiments on twelve tasks spanning question answering, summarization, and translation across four different LLMs, we show that RAUQ consistently outperforms state-of-the-art UQ baselines. Importantly, it does so with minimal cost, less than 1% additional computation. Since it requires neither labeled data nor extensive parameter tuning, RAUQ serves as a lightweight, plug-and-play solution for real-time hallucination detection in white-box LLMs.