Persona Steering Silences Model Refusals, Revealing Safety's Hidden Dependency
In Qwen2.5 and Llama‑3.1, researchers extracted linear directions for a compliant persona and for refusal. Removing the persona direction drops refusal rates from 97% to 2%, showing that safety refusals are gated by downstream persona activations. This means alignment tricks that tweak persona can unintentionally mute or amplify refusal behavior.