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

翻译：尽管在思维链（CoT）等提示技术方面取得了进展，数学推理对于大语言模型（LLMs）而言仍然是一个重大挑战。我们提出了数学标注思维链（CoMAT），它通过两个阶段来增强推理能力：符号转换（将自然语言查询转换为符号形式）和推理执行（从符号表示中推导答案）。CoMAT完全在单个LLM内部运行，无需外部求解器。在四个LLM上，CoMAT在七个基准测试中的六个上优于传统CoT，在MMLU-Redux（MATH）上实现了4.48%的性能提升，在GaoKao MCQ上实现了4.58%的提升。除了性能改进之外，CoMAT确保了忠实性和可验证性，为复杂的数学任务提供了透明的推理过程。