AI RESEARCH

GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought

arXiv CS.AI

ArXi:2605.26893v1 Announce Type: cross Chain-of-Thought (CoT) reasoning has advanced large language models (LLMs), but outcome-based supervision leads to pervasive post-hoc rationalization, producing plausible yet unfaithful reasoning chains. Most prior faithfulness assessment methods are either unscalable, expensive, or unreliable. We propose GeoFaith, a spatio-temporal framework that leverages latent geometric structure and entropy dynamics to diagnose and enforce faithful reasoning.