Refusal Lives Downstream of Persona in Chat Models
본문 미리보기
arXiv:2606.26161v1 Announce Type: new Abstract: Linear directions in activation space have been identified for both refusal and persona traits in instruction-tuned chat models, but the two have been studied as separate mechanisms. We show they interact: a compliant persona gates refusal. In Qwen2.5-7B-Instruct and Llama-3.1-8B-Instruct, we extract a compliant model-persona direction and a refusal direction and intervene on both. Compliant persona steering suppresses refusal -- in Llama, the ref
전체 내용이 궁금하다면?
원문을 직접 읽어보세요