SOURCE-LINKED INTELLIGENCE

When Steering Fails in Latent Reasoning: A Latent-to-Language Transition Gap

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Activation steering has become a widely used approach for controlling language models during explicit chain-of-thought (CoT) reasoning, motivating its extension to latent CoT. However, we find that steering continuous thoughts produces substantially weaker effects on subsequent language generation than steering explicit CoT, even when the hidden representations are moved by comparable amounts. We first show that task information remains identifiable in continuous thoughts. Hence, we hypothesize a \textbf{latent-to-language transition gap}, in which an intervention effect in latent space fails

Read original source ↗ Open in workspace

recordType

paper

region

Global