output
20032025
most citedEmergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

25 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing 2003 · cs.CLShow all

Nothing from here under that filter.

Their other years and fields are still on the left.

Show all their papers