Zifan Carl Guo

@zifan-carl-guo · 1 works

AI researcher studying when language models generate faithful explanations versus superficial imitations.

Recent posts by Zifan Carl Guo

• Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision - When does training language models (LMs) to generate explanations of their predictions yield faithful introspection, rather than superficial imitation? We study LMs trained to explain which features… · Paper · arxiv.org