Safety Alignment of LMs via Non-cooperative Games 文章

ArXiv CS.AI2026-06-02NEWSen作者: Anselm Paulus, Ilia Kulikov, Brandon Amos, R\'emi Munos, Ivan Evtimov, Kamalika Chaudhuri, Arman Zharmagambetov
查看原文 →
关系图谱

Safety Alignment of LMs via Non-cooperative Games · 相关技术

相关技术

language modelreinforcement learningAdvGame