层次化思维链提示：提升大语言模型推理性能与效率
Hierarchical Chain-of-Thought: Enhancing LLM Reasoning Performance and Efficiency
AI总结：
本文提出层次化思维链提示方法，通过分层步骤规划与执行提升复杂多步推理的准确率和效率，实验显示在多种模型和任务中平均准确率提升6.2%。
摘要：
链式思维（CoT）提示显著提升了大语言模型（LLMs）的推理能力。然而，传统CoT常依赖无结构的扁平推理链，导致冗余和性能不佳。本文引入层次化链式思维（Hi-CoT）提示，是一种专门设计用于解决复杂多步推理挑战的结构化推理范式。Hi-CoT通过交替进行指令规划和逐步执行，将推理过程分解为层次化的子步骤。这种分解使LLMs能够更好地管理长推理范围并保持逻辑一致性。在多样化的LLMs和数学推理基准上的广泛评估表明，与CoT提示相比，Hi-CoT在平均准确率上提高了6.2%（某些模型和任务达到61.4%），同时将推理轨迹长度减少了13.9%。我们进一步表明，当模型严格遵循层次结构时，准确率和效率达到最大值。我们的代码可在https://github.com/XingshuaiHuang/Hi-CoT上获取。
英文摘要：
Chain-of-Thought (CoT) prompting has significantly improved the reasoning capabilities of large language models (LLMs). However, conventional CoT often relies on unstructured, flat reasoning chains that suffer from redundancy and suboptimal performance. In this work, we introduce Hierarchical Chain-of-Thought (Hi-CoT), a structured reasoning paradigm specifically designed to address the challenges of complex, multi-step reasoning. Hi-CoT decomposes the reasoning process into hierarchical substeps by alternating between instructional planning and step-by-step execution. This decomposition enables LLMs to better manage long reasoning horizons and maintain logical coherence. Extensive evaluations across diverse LLMs and mathematical reasoning benchmarks show that Hi-CoT consistently improves average accuracy by 6.2% (up to 61.4% on certain models and tasks) while reducing reasoning trace length by 13.9% compared to CoT. We further show that accuracy and efficiency are maximized when models strictly adhere to the hierarchical structure. Our code is available at https://github.com/XingshuaiHuang/Hi-CoT.
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。
