Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications 文章

ArXiv CS.AI2026-05-26NEWSen作者: Xiaoyue Lu, Xianglin Yang, Haijun Liu, Jiahao Liu, Kuntai Cai, Yan Xiao, Jin Song Dong
大语言模型
查看原文 →
关系图谱

Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications · 相关人物

暂无数据