Recent advances in large language models (LLMs) have leveraged explicit Chain-of-Thought (CoT) prompting to improve reasoning accuracy. However, most existing methods primarily focus on compressing verbose reasoning outputs. These Long-to-Short transformations aim to improve efficiency, but require a large amount of short CoT data. In this work, we introduce \textbf{3TF} (\textbf{T}hought-\textbf{T}raining and \textbf{T}hought-\textbf{F}ree inference), a framework for efficient reasoning that takes a Short-to-Long perspective. We first train a hybrid model that can operate in both reasoning and non-reasoning modes, and then further train it on CoT-annotated data to internalize structured reasoning, while enforcing concise, thought-free outputs at inference time using the no-reasoning mode. Unlike compression-based approaches, 3TF improves the reasoning quality of non-reasoning outputs, enabling models to perform rich internal reasoning implicitly while keeping external outputs short. Empirically, 3TF-trained models obtain large improvements on reasoning benchmarks under thought-free inference, demonstrating that high quality reasoning can be learned and executed implicitly without explicit step-by-step generation.
翻译:近期大型语言模型(LLMs)的进展通过显式的思维链(CoT)提示来提升推理准确性。然而,现有方法大多侧重于压缩冗长的推理输出。这些从长到短的转换旨在提高效率,但需要大量短CoT数据。本文提出\\textbf{3TF}(\\textbf{T}hought-\\textbf{T}raining and \\textbf{T}hought-\\textbf{F}ree inference)框架,采用从短到长的视角实现高效推理。我们首先训练一个可在推理与非推理模式下运行的混合模型,随后在CoT标注数据上进一步训练,以内部化结构化推理,同时在推理时使用非推理模式强制生成简洁的无思维输出。与基于压缩的方法不同,3TF提升了非推理输出的推理质量,使模型能够隐式执行丰富的内部推理,同时保持外部输出简短。实验表明,经3TF训练的模型在无思维推理下的推理基准测试中取得显著提升,证明高质量推理可通过隐式学习与执行实现,无需显式的逐步生成。