EntroCoT：通过自适应熵引导分割增强链式思考
EntroCoT: Enhancing Chain-of-Thought via Adaptive Entropy-Guided Segmentation
AI总结：
EntroCoT通过自适应熵引导分割提升链式思考的推理质量，构建高质量数据集以提高大语言模型的数学推理能力。
摘要：
链式思考（CoT）提示方法显著增强了大语言模型的数学推理能力。我们发现现有微调数据集经常存在"答案正确但推理错误"的问题，其中正确最终答案是通过幻觉、冗余或逻辑无效的中间步骤得出的。本文提出EntroCoT，这是一个统一的框架，用于自动识别和改进低质量的CoT监督轨迹。EntroCoT首先提出一种基于熵的机制，在不确定的转折点将推理轨迹分割成多个步骤，然后引入基于蒙特卡洛滚动的机制来评估每一步的边际贡献。通过准确过滤欺骗性推理样本，EntroCoT构建了一个高质量的数据集，其中每个推理轨迹中的每个中间步骤都促进最终答案。在数学基准上的广泛实验表明，对由EntroCoT构建的子集进行微调，其性能始终优于全数据集监督的基线。
英文摘要：
Chain-of-Thought (CoT) prompting has significantly enhanced the mathematical reasoning capabilities of Large Language Models. We find existing fine-tuning datasets frequently suffer from the "answer right but reasoning wrong" probelm, where correct final answers are derived from hallucinated, redundant, or logically invalid intermediate steps. This paper proposes EntroCoT, a unified framework for automatically identifying and refining low-quality CoT supervision traces. EntroCoT first proposes an entropy-based mechanism to segment the reasoning trace into multiple steps at uncertain junctures, and then introduces a Monte Carlo rollout-based mechanism to evaluate the marginal contribution of each step. By accurately filtering deceptive reasoning samples, EntroCoT constructs a high-quality dataset where every intermediate step in each reasoning trace facilitates the final answer. Extensive experiments on mathematical benchmarks demonstrate that fine-tuning on the subset constructed by EntroCoT consistently outperforms the baseslines of full-dataset supervision.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
