Employing Large Language Models (LLMs) to address mathematical problems is an intriguing research endeavor, considering the abundance of math problems expressed in natural language across numerous science and engineering fields. While several prior works have investigated solving elementary mathematics using LLMs, this work explores the frontier of using GPT-4 for solving more complex and challenging math problems. We evaluate various ways of using GPT-4. Some of them are adapted from existing work, and one is \MathChat, a conversational problem-solving framework newly proposed in this work. We perform the evaluation on difficult high school competition problems from the MATH dataset, which shows the advantage of the proposed conversational approach.

翻译：利用大语言模型（LLMs）解决数学问题是一项引人入胜的研究探索，考虑到众多科学与工程领域中大量以自然语言表达的数学问题。尽管已有若干前期工作研究了使用LLMs求解初等数学问题，本研究则探索了利用GPT-4解决更复杂、更具挑战性数学问题的前沿领域。我们评估了多种使用GPT-4的方式，其中部分方法改编自现有工作，而\MathChat（本研究新提出的对话式问题解决框架）则是其中之一。我们在MATH数据集中难度较高的高中竞赛题目上进行了评估，结果表明所提出的对话式方法具有明显优势。