1
SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
大模型安全新方案：局部在策略蒸馏实现高效安全对齐，论文已提交EMNLP 2026。
arXiv:2606.02530v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, ter…