Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment
·
0 次浏览
·来源: ArXiv AI
arXiv:2610.07023v1 Announce Type: new Abstract: 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...
arXiv:2610.07023v1 Announce Type: new Abstract: 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...
arXiv:2610.07023v1 Announce Type: new Abstract: 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...