让模型在不输出思考过程的情况下仍能高效推理。
Efficient Reasoning via Thought-Training and Thought-Free Inference
- 训练模型在推理与非推理模式间切换，隐式学习逻辑链。
- 无需显式生成步骤，推理准确率提升显著。
- 适合需要快速响应且保持高推理质量的场景。
近年来大语言模型通过显式的思维链（Chain-of-Thought, CoT）提示提升了推理准确性。然而，现有方法多聚焦于压缩冗长的推理输出，依赖大量简短思维链数据，难以推广。本文提出3TF（Thought-Training and Thought-Free inference）框架，采用从短到长的新范式：先训练一个可切换推理与非推理模式的混合模型，再在标注有思维链的数据上进一步训练，使其内化结构化推理能力；推理时强制使用非推理模式，实现无思考过程的简洁输出。与压缩类方法不同，3TF不仅保持输出简短，还提升了非推理输出的推理质量，使模型能隐式完成复杂推理。实验表明，3TF训练的模型在无思考输出下于多个推理基准上取得显著提升，证明高质量推理可在无需显式生成步骤的情况下被学习并执行。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。