From Recall to Reasoning: Automated Question Generation for Deeper Math Learning through Large Language Models

TL;DR

This paper explores how large language models can generate high-quality math practice problems to enhance advanced math education, identifying best practices for effective AI-assisted content creation.

Contribution

It evaluates current GenAI capabilities for math problem generation and proposes an improved framework to enhance output quality and relevance.

Findings

GenAI can produce math problems of varying quality with minimal support.

Providing examples and relevant content improves problem quality.

The study offers guidelines for educators to effectively adopt GenAI in math education.

Abstract

Educators have started to turn to Generative AI (GenAI) to help create new course content, but little is known about how they should do so. In this project, we investigated the first steps for optimizing content creation for advanced math. In particular, we looked at the ability of GenAI to produce high-quality practice problems that are relevant to the course content. We conducted two studies to: (1) explore the capabilities of current versions of publicly available GenAI and (2) develop an improved framework to address the limitations we found. Our results showed that GenAI can create math problems at various levels of quality with minimal support, but that providing examples and relevant content results in better quality outputs. This research can help educators decide the ideal way to adopt GenAI in their workflows, to create more effective educational experiences for students.