What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding

Published: 07 Jul 2025, Last Modified: 07 Jul 2025KnowFM @ ACL 2025EveryoneRevisionsBibTeXCC BY 4.0
Keywords: Large language Model, Reasoning, Generation, Speculative Decoding, Alignment
TL;DR: We systematically analyze the token distribution misalignment for large reasoning models and propose a novel collaborative decoding method.
Abstract: Large reasoning models (LRMs) achieve strong reasoning performance by emitting long chains of thought. Yet, these verbose traces slow down inference and often drift into unnecessary detail, known as the overthinking phenomenon. To better understand LRMs' behavior, we systematically analyze the token-level misalignment between reasoning and non-reasoning models. While it is expected that their primary difference lies in the stylistic "thinking cues", LRMs uniquely exhibit two pivotal, previously under-explored phenomena: a Global Misalignment Rebound, where their divergence from non-reasoning models persists or even grows as response length increases, and more critically, a Local Misalignment Diminish, where the misalignment concentrates at the "thinking cues" each sentence starts with but rapidly declines in the remaining of the sentence. Motivated by the Local Misalignment Diminish, we propose FoReaL-Decoding, a collaborative fast-slow thinking decoding method for cost-quality trade-off. In FoReaL-Decoding, a Leading model leads the first few tokens for each sentence, and then a weaker draft model completes the following tokens to the end of each sentence. FoReaL-Decoding adopts a stochastic gate to smoothly interpolate between the small and the large model. On four popular math-reasoning benchmarks (AIME24, GPQA-Diamond, MATH500, AMC23), FoReaL-Decoding reduces theoretical FLOPs by $30$ – $50\%$ and trims CoT length by up to $40\%$, while preserving $86$ – $100\%$ of model performance. These results establish FoReaL-Decoding as a simple, plug-and-play route to controllable cost-quality trade-offs in reasoning-centric tasks.
Archival Status: Non-archival (not included in proceedings)
Submission Number: 23
Loading