★原文链接:https://zhuanlan.zhihu.com/p/1998418717743289472作者:王云鹤写这个的时候,其实我脑子里第一反应是好多年以前某位领导问过我,transformer的下一跳是什么?
As LLMs and diffusion models power more applications, their safety alignment becomes critical. Our research shows that even minimal downstream fine‑tuning can weaken safeguards, raising a key question ...