Consistency Training Along the Transformer Stack 文章

ArXiv CS.AI2026-06-06NEWSen作者: Sukrati Gautam, Neil Shah, Arav Dhoot, Bryan Maruyama, Caroline Wei, Rohan Kapoor, Robert Sidey, Prakhar Gupta, Zi Cheng Huang, David Demitri Africa
AI 安全
查看原文 →
关系图谱

Consistency Training Along the Transformer Stack · 相关技术

相关技术

jailbreakssycophancyconditional misalignmentprefill attacksadversarial frustrationpersona in-context learning attacksAttention Consistency TrainingConsistency training