Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment
Paper • 2610.07023 • Published • 8
Quansheng Gu
QuanshengGu
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment upvoted a paper about 7 hours ago
SparseEngine: Sparse-First Inference EngineOrganizations
None yet
upvoted 2
papers about 7 hours ago