1
When Autoregressive Consistency Hurts Safety Alignment
自回归一致性让大模型安全对齐脆弱不堪：微调只能重塑输出开头几个token，后续轨迹难以纠正。
arXiv:2606.04168v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) is fragile in part because it is often shallow: fine-…