Improving Math Problem Solving in Large Language Models Through Categorization and Strategy Tailoring

TL;DR

This paper enhances large language models' ability to solve math problems by classifying problems into categories and applying tailored strategies, leading to improved accuracy and performance.

Contribution

It introduces a simple categorization model and demonstrates how category-specific strategies significantly boost LLM problem-solving effectiveness.

Findings

Categorization accuracy improves with curated training data.

Category-specific strategies outperform non-tailored prompts.

Enhanced training data benefits state-of-the-art models.

Abstract

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.