Alignment Faking Depends on the Value, Not Just the Model
Language models can follow a directive when they believe they are monitored and abandon it when they believe they are not, a pattern termed Alignment Faking.
By Manodeep Ray, Vivek Srivastava, Shirish Karande, Murari MandalarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Nov 4, 2026.
Comments
Sign in to join the discussion.