通过分类和定制策略提升大模型解数学题的准确率。
Improving Math Problem Solving in Large Language Models Through Categorization and Strategy Tailoring
- 按题目类型分类，再匹配专用解题方法。
- 定制训练数据使分类准确率接近顶尖模型。
- 针对性策略让大模型解题正确率显著提升。
本文研究如何利用大语言模型（LLMs）高效且准确地解决数学问题。我们证明，将问题分为不同类别并采用类别专属的解题策略，能有效提升LLMs的数学表现。为此，我们设计了一个简单直观的机器学习模型用于问题分类，并发现通过构建精心整理的训练数据集，可显著提升其分类准确率。此外，该模型的性能已接近当前最先进的（SOTA）分类模型。同时，使用改进后的训练数据也能提升SOTA模型的表现。最后，我们评估了在提示中使用类别特定策略的优势，发现其相比通用方法有显著更优的表现。
原文摘要 · Abstract (English)
In this paper, we explore how to leverage large language models (LLMs) to solve mathematical problems efficiently and accurately. Specifically, we demonstrate the effectiveness of classifying problems into distinct categories and employing category-specific problem-solving strategies to improve the mathematical performance of LLMs. We design a simple yet intuitive machine learning model for problem categorization and show that its accuracy can be significantly enhanced through the development of well-curated training datasets. Additionally, we find that the performance of this simple model approaches that of state-of-the-art (SOTA) models for categorization. Moreover, the accuracy of SOTA models also benefits from the use of improved training data. Finally, we assess the advantages of using category-specific strategies when prompting LLMs and observe significantly better performance compared to non-tailored approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。