Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment
Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to jailbreak attacks that elicit harmful or unsafe outputs. Existing safety alignment approaches, including Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), often require substantial attack-specif...
Jin-Hao Pang, Jitai Hao, Qiang Huang et al.
· 0 citations