Shauli Ravfogel(@ravfogel):1/ Can LLMs introspect, i.e., reason about their internal states? Recent work claims LLMs notice when their "thoughts" get tampered with, and can report their content. We looked closely and we think it's too early to say that. Work led by @shashwat

Shauli Ravfogel

@ravfogel

Faculty fellow at NYU CDS. Previously: PhD @ BIU NLP

参加 September 2018

1.3K フォロー中 1.8K ファン

Shauli Ravfogel@ravfogel

2026.05.28 13:16

1/ Can LLMs introspect, i.e., reason about their internal states? Recent work claims LLMs notice when their "thoughts" get tampered with, and can report their content. We looked closely and we think it's too early to say that. Work led by @shashwat_s19 , with @tallinzen and me.