Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction
Paper • 2509.15202 • Published • 2
OpenCAS
OpenCAS
AI & ML interests
None yet
Recent Activity
liked a model 18 days ago
skysys00/Meta-Llama-3-8B-Instruct-DeepRefusal upvoted a paper 7 months ago
A Survey of Vibe Coding with Large Language ModelsOrganizations
None yet