When LLMs Learn to Be Consistently Wrong: A Multi-Model Study of Linear Representations of Synthetic Deception 文章

ArXiv CS.AI2026-06-01NEWSen作者: Vahideh Zolfaghari
查看原文 →
关系图谱

When LLMs Learn to Be Consistently Wrong: A Multi-Model Study of Linear Representations of Synthetic Deception · 相关事件

暂无数据