SOURCE-LINKED INTELLIGENCE

Think Wider: Mitigating Latent Rank Collapse in Implicit Chain-of-Thought Reasoning

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Chain-of-thought (CoT) reasoning improves the reasoning ability of large language models by introducing intermediate computation, but explicit rationales increase decoding length, latency, and context cost. Implicit CoT offers a more efficient alternative by moving intermediate reasoning into continuous latent states. However, latent reasoning can be unstable: successive latent states may become overly similar and collapse toward a shared dominant direction, reducing the diversity of the reasoning trajectory. In this work, we identify $\textit{latent rank collapse}$ and propose $\textbf{WIDER}

Read original source ↗ Open in workspace

recordType

paper

region

Global