Jingyuan Feng, Andrew Gambardella, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment

arXiv:2603.06727v1 Announce Type: new Abstract: Current safety alignment methods encode safe behavior implicitly within model parameters, creating a fundamental opacity: we cannot easily inspect why …