Minjong Cheon

Robust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science Skepticism

It is argued that behavioral evaluation alone cannot distinguish a model that resists skepticism because it understands the signal from one that only appears to resist because it fails to perceive it, and that robustness does not transfer: it attenuates across domains and can reverse, with myth-rebuttal weakening under skeptical pressure.