CoMAT：数学注释的思维链提升数学推理
CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning
AI总结：
CoMAT通过符号转换和推理执行两个阶段提升数学推理能力，在多个基准测试中超越传统CoT方法。
摘要：
数学推理仍然是大型语言模型（LLMs）面临的重要挑战，尽管在提示技术如思维链（CoT）方面取得了进展。我们提出了**数学注释的思维链（CoMAT）**，通过两个阶段增强推理：*符号转换*（将自然语言查询转换为符号形式）和*推理执行*（从符号表示中推导出答案）。CoMAT完全使用单一LLM运行，无需外部求解器。在四款LLM上，CoMAT在七个基准中的六个上优于传统CoT，实现了在MMLU-Redux（MATH）上的4.48%提升和在GaoKao MCQ上的4.58%提升。除了性能提升外，CoMAT确保了准确性和可验证性，为复杂的数学任务提供透明的推理过程。
英文摘要：
Mathematical reasoning remains a significant challenge for large language models (LLMs), despite progress in prompting techniques such as Chain-of-Thought (CoT). We present **Chain of Mathematically Annotated Thought (CoMAT)**, which enhances reasoning through two stages: *Symbolic Conversion* (converting natural language queries into symbolic form) and *Reasoning Execution* (deriving answers from symbolic representations). CoMAT operates entirely with a single LLM and without external solvers. Across four LLMs, CoMAT outperforms traditional CoT on six out of seven benchmarks, achieving gains of 4.48% on MMLU-Redux (MATH) and 4.58% on GaoKao MCQ. In addition to improved performance, CoMAT ensures faithfulness and verifiability, offering a transparent reasoning process for complex mathematical tasks
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。
