Question. Suppose we call the kind of unrepetant boot-licking (“I apologize for the error”) that LLMs often do “chatlighting” (h/t @Dolimac
). Why exactly is chatlighting so frequent? Is it a consequence of RLHF? Do we see the same chatlighting behavior in “base models” without
Chatlighting in LLMs: RLHF’s Role in Obsequious Responses
By
–
