让大模型按需调整推理深度，提升问答准确率
Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute
- 用可调强度的隐向量控制推理深度，无需训练
- 在GSM8K等数据集上显著提升准确率
- 适合需要灵活推理的复杂任务场景
测试时计算已成为提升大语言模型性能的强大范式，通过生成多个输出或精炼单个推理链可显著提高答案准确性。然而，现有方法如Best-of-N、多数投票和自反思通常对所有输入采用统一推理方式，忽略了不同问题所需的推理深度不同。本文提出分数推理（Fractional Reasoning），一种无需训练且与模型无关的框架，可在推理时连续调节推理强度，突破固定提示词的局限。该方法通过提取深层推理对应的隐向量，并以可调缩放因子重新应用，使模型能根据输入复杂度动态调整推理过程。支持两种测试时扩展模式：(1) 提升基于广度策略（如Best-of-N、多数投票）的输出质量；(2) 增强基于深度策略（如自反思）的单条推理链正确性。在GSM8K、MATH500和GPQA上的实验表明，分数推理在多种推理任务和模型上均持续提升性能。
原文摘要 · Abstract (English)
Test-time compute has emerged as a powerful paradigm for improving the performance of large language models (LLMs), where generating multiple outputs or refining individual chains can significantly boost answer accuracy. However, existing methods like Best-of-N, majority voting, and self-reflection typically apply reasoning in a uniform way across inputs, overlooking the fact that different problems may require different levels of reasoning depth. In this work, we propose Fractional Reasoning, a training-free and model-agnostic framework that enables continuous control over reasoning intensity at inference time, going beyond the limitations of fixed instructional prompts. Our method operates by extracting the latent steering vector associated with deeper reasoning and reapplying it with a tunable scaling factor, allowing the model to tailor its reasoning process to the complexity of each input. This supports two key modes of test-time scaling: (1) improving output quality in breadth-based strategies (e.g., Best-of-N, majority voting), and (2) enhancing the correctness of individual reasoning chains in depth-based strategies (e.g., self-reflection). Experiments on GSM8K, MATH500, and GPQA demonstrate that Fractional Reasoning consistently improves performance across diverse reasoning tasks and models.
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。