1
On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
新型对齐范式on-policy一致性训练，在提升LLM安全性同时极小化能力退化，是安全对齐的重要突破。
arXiv:2605.21834v1 Announce Type: new Abstract: Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, o…