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

Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention arXiv:2606.01243v1 Announce Type: new Abstract: Latent reasoning enables Large Language Models (LLMs) to perform multi-step inference within continuous hidden states, offering efficiency gains over explicit Chain-of-Thought (CoT). However, the opacity of these continuous thought vectors hinders their reliability and controllability. This paper bridges the gap between mechanistic interpretability and