Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention 文章

ArXiv CS.CL2026-06-02NEWSen作者: Shuochen Chang, Tong Bai, Xiaofeng Zhang, Qianli Ma, Qingyang Liu, Zhaohe Liao, Yibo Miao, Li Niu
查看原文 →
关系图谱

Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention · 相关技术

相关技术

Mechanistic Interpretabilitylatent vectorslatent reasoningchain-of-thoughtlarge language models