作者位次 #7/13ACL 2026Poster· Natural Language Processing
Hallucination Detection in LLM s with Topological Divergence on Attention Graphs
Alexandra Bazarova · Andrei Volodichev · Aleksandr Yugay · Andrey Shulga · Alina Ermilova · Konstantin Polev · Julia Belikova · Rauf Parchiev · Dmitry Simakov · Maxim Savchenko · Andrey V. Savchenko · Serguei Barannikov · Alexey Zaytsev
摘要
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 leve...