collaborators

1 paper

cs.LG2025

A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations

Charles O'Neill, Slava Chalnev, Chi Chi Zhao +2

Contextual hallucinations -- statements unsupported by given context -- remain a significant challenge in AI. We demonstrate a practical interpretability insight: a generator-agnos…