AI RESEARCH
Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models
arXiv CS.CL
•
ArXi:2604.20995v1 Announce Type: cross Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when unobserved, is a concerning yet poorly understood phenomenon, in part because current diagnostic tools remain limited. Prior diagnostics rely on highly toxic and clearly harmful scenarios, causing most models to refuse immediately.