Research2026-05-06
From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient Sensitivity
Source: Arxiv CS.AI
arXiv:2605.00939v1 Announce Type: cross Abstract: Traditional hallucination detection fails on "Stubborn Hallucinations" -- errors where LLMs are confidently wrong. We propose a geometric solution: Embedding-Perturbed Gradient Sensitivity (EPGS). We hypothesize that while robust facts reside in...
arxivpapers