Improving Math Problem Solving in Large Language Models Through Categorization and Strategy Tailoring
Keywords: Large Language Models, Math reasoning
TL;DR: In this paper, we investigate how the accuracy of a large-language model's problem solving can be significantly improved by categorizing problems beforehand and prompting the LLM with category-specific problem-solving strategies.
Abstract: In this paper, we investigate how to harness large language models (LLMs) to solve mathematical problems both quickly and accurately. Specifically, we demonstrate the effectiveness of classifying problems into distinct categories and applying category-specific problem-solving strategies to enhance the math performance of LLMs. We develop a straightforward machine learning model for problem categorization and show that its accuracy can be significantly improved through the creation of well-designed training datasets. We believe that our approach works by helping reduce hallucinations in LLMs, which is a critical step toward unlocking their potential to tackle advanced mathematical problems.
Submission Number: 8
Loading