← all papers · overview

SPOT: Span-level Pause-of-thought For Efficient And Interpretable Latent Reasoning In Large Language Models

Abstract

Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step pruning, they largely truncate what the model says rather than internalize what the model thinks. Latent reasoning offers a promising alternative by performing computa

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).