Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models (LLMs). We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting, 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 reveals consistent patterns: higher divergence values in specific attention heads correlate with hallucinated outputs, independent of the dataset. Extensive experiments - including evaluation 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 suggest that analyzing the topological structure of attention matrices can serve as an efficient and robust indicator of factual reliability in LLMs.
@article{arxiv.2504.10063,
title = {Hallucination Detection in LLMs with Topological Divergence on Attention Graphs},
author = {Alexandra Bazarova and Andrei Volodichev and Aleksandr Yugay and Andrey Shulga and Alina Ermilova and Konstantin Polev and Julia Belikova and Rauf Parchiev and Dmitry Simakov and Maxim Savchenko and Andrey Savchenko and Serguei Barannikov and Alexey Zaytsev},
journal= {arXiv preprint arXiv:2504.10063},
year = {2026}
}
Comments
Accepted to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)