RM-PoT：重构数学问题并通过思维程序求解
RM-PoT: Reformulating Mathematical Problems and Solving via Program of Thoughts
AI总结：
针对大型语言模型（LLMs）在复杂数学问题推理时对表面形式变化鲁棒性不足的问题，提出RM-PoT三阶段框架，通过问题重构、领域少样本示例检索及代码辅助推理提升求解性能。
摘要：
近期，在训练语言模型执行逐步推理以解决复杂数值推理任务方面取得了重大进展。除了解决这些问题的方法外，问题本身的结构和表述在决定大型语言模型的性能方面也起着关键作用。我们观察到，即使数学问题的表面形式发生微小变化，也会对答案分布和求解率产生深远影响。这凸显了大型语言模型（LLMs）对表面级变化的脆弱性，揭示了其在复杂问题推理时鲁棒性有限的问题。本文提出RM-PoT，这是一个三阶段框架，整合了问题重构（RM）、代码辅助推理（PoT）和领域感知少样本学习来解决这些局限性。我们的方法首先将输入问题重构为多种表面形式以减少结构偏差，然后从预先构建的领域特定题库中检索五个语义对齐的示例以提供上下文指导，最后生成可执行的Python代码以进行精确计算。
英文摘要：
Recently, substantial advancements have been made in training language models to carry out step-by-step reasoning for solving intricate numerical reasoning tasks. Beyond the methods used to solve these problems, the structure and formulation of the problems themselves also play a crucial role in determining the performance of large language models. We observe that even small changes in the surface form of mathematical problems can have a profound impact on both the answer distribution and solve rate. This highlights the vulnerability of LLMs to surface-level variations, revealing its limited robustness when reasoning through complex problems. In this paper, we propose RM-PoT, a three-stage framework that integrates problem reformulation (RM), code-aided reasoning (PoT), and domain-aware few-shot learning to address these limitations. Our approach first reformulates the input problem into diverse surface forms to reduce structural bias, then retrieves five semantically aligned examples from a pre-constructed domain-specific question bank to provide contextual guidance, and finally generates executable Python code for precise computation.
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。
