PRISM: Recovering Instruction Sets from Language Model Activations 文章

ArXiv CS.AI2026-06-09NEWSen作者: Gilad Gressel, Rahul Pankajakshan, Julia Diament, Efim Hudis, Krishnashree Achuthan, Yisroel Mirsky

PRISM: Recovering Instruction Sets from Language Model Activations · 相关人物

暂无数据