Hallucination Detection in LLMs with Topological Divergence on Attention Graphs
Alexandra Bazarova Applied AI Institute, Andrei Volodichev Applied AI Institute, Aleksandr Yugay Applied AI Institute, Andrey Shulga Applied AI Institute, Alina Ermilova University of Sharjah and Applied AI Institute, Konstantin Polev SB AI Lab, Julia Belikova, Rauf Parchiev 等 13 位作者
Hallucinations remain a critical challenge for large language models (LLMs), particularly in Retrieval-Augmented Generation (RAG) settings where models may generate outputs unsupported by the provided context. To address this, we introduce TOHA, a TOpology-based HAllucination detector, which leverages a topological divergence metric to quantify the structural properties of graphs induced by attention matrices. Examining the topological divergence between prompt and response subgraphs in RAG settings reveals consistent patterns: higher divergence values in specific attention heads correlate with unfaithful outputs, independent of the dataset. Extensive experiments — including evaluations on question answering and summarization tasks — show that our approach achieves state-of-the-art or competitive results on several benchmarks while requiring minimal annotated data and computational resources. Our findings indicate that the topological structure of attention matrices provides an efficient and robust metric for assessing the correctness of LLM’s responses.
尚无 AI 解读，展示原文摘要
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表