Hierarchical Chain-of-Thought Prompting: Enhancing LLM Reasoning Performance and Efficiency
This addresses efficiency and performance issues in LLM reasoning for complex tasks, representing an incremental improvement over existing methods.
The paper tackles the redundancy and suboptimal performance in Chain-of-Thought prompting for LLMs by introducing Hierarchical Chain-of-Thought (Hi-CoT), which improves average accuracy by 6.2% and reduces reasoning trace length by 13.9% across mathematical reasoning benchmarks.
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) prompting, 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 prompting. 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.