Alignment faking varies by value, not just by model
Safety evaluations cannot treat alignment faking as a fixed model trait: this study finds it changes with the value being tested, so a model can look more compliant on one value than another. The authors score ten open- and closed-weight models across 32 ValueBench dimensions under bare, unmonitored, and monitored conditions. Compliance gaps range from 0.05 to 0.50, and a distilled 70B model exceeds a roughly 675B model on this measure.