Generative AI for Enhancing Active Learning in Education: A Comparative Study of GPT-3.5 and GPT-4 in Crafting Customized Test Questions

TL;DR

This paper compares GPT-3.5 and GPT-4 in generating and teaching customized math questions for active learning, showing GPT-4's superior question quality and GPT-3.5's improved problem-solving after instruction.

Contribution

It introduces a novel iterative method for LLMs to develop and refine educational questions, demonstrating GPT-4's advanced capabilities in this context.

Findings

GPT-4 generates more precise and challenging questions.

GPT-3.5 improves in handling complex problems after GPT-4's instruction.

The study highlights LLMs' potential to support personalized active learning.

Abstract

This study investigates how LLMs, specifically GPT-3.5 and GPT-4, can develop tailored questions for Grade 9 math, aligning with active learning principles. By utilizing an iterative method, these models adjust questions based on difficulty and content, responding to feedback from a simulated 'student' model. A novel aspect of the research involved using GPT-4 as a 'teacher' to create complex questions, with GPT-3.5 as the 'student' responding to these challenges. This setup mirrors active learning, promoting deeper engagement. The findings demonstrate GPT-4's superior ability to generate precise, challenging questions and notable improvements in GPT-3.5's ability to handle more complex problems after receiving instruction from GPT-4. These results underscore the potential of LLMs to mimic and enhance active learning scenarios, offering a promising path for AI in customized education. This research contributes to understanding how AI can support personalized learning experiences, highlighting the need for further exploration in various educational contexts