Learning gain differences between ChatGPT and human tutor generated algebra hints

TL;DR

This study compares the effectiveness of ChatGPT-generated algebra hints with human tutor hints, finding that human hints lead to significantly higher learning gains despite ChatGPT producing mostly acceptable hints.

Contribution

First evaluation of ChatGPT's algebra hints in a tutoring context, demonstrating its potential and limitations compared to human-authored hints.

Findings

ChatGPT hints passed 70% quality checks

Human hints resulted in significantly higher learning gains

ChatGPT performance was near ceiling in Intermediate Algebra

Abstract

Large Language Models (LLMs), such as ChatGPT, are quickly advancing AI to the frontiers of practical consumer use and leading industries to re-evaluate how they allocate resources for content production. Authoring of open educational resources and hint content within adaptive tutoring systems is labor intensive. Should LLMs like ChatGPT produce educational content on par with human-authored content, the implications would be significant for further scaling of computer tutoring system approaches. In this paper, we conduct the first learning gain evaluation of ChatGPT by comparing the efficacy of its hints with hints authored by human tutors with 77 participants across two algebra topic areas, Elementary Algebra and Intermediate Algebra. We find that 70% of hints produced by ChatGPT passed our manual quality checks and that both human and ChatGPT conditions produced positive learning gains. However, gains were only statistically significant for human tutor created hints. Learning gains from human-created hints were substantially and statistically significantly higher than ChatGPT hints in both topic areas, though ChatGPT participants in the Intermediate Algebra experiment were near ceiling and not even with the control at pre-test. We discuss the limitations of our study and suggest several future directions for the field. Problem and hint content used in the experiment is provided for replicability.