Evaluating the Application of Large Language Models to Generate Feedback in Programming Education
This addresses the need for scalable feedback in programming education, but it is incremental as it applies existing models to a specific domain.
This study tackled the problem of providing automated feedback in programming education by applying GPT-4 to generate feedback on programming tasks, finding that most feedback effectively addressed code errors but faced challenges with incorrect suggestions and hallucinated issues.
This study investigates the application of large language models, specifically GPT-4, to enhance programming education. The research outlines the design of a web application that uses GPT-4 to provide feedback on programming tasks, without giving away the solution. A web application for working on programming tasks was developed for the study and evaluated with 51 students over the course of one semester. The results show that most of the feedback generated by GPT-4 effectively addressed code errors. However, challenges with incorrect suggestions and hallucinated issues indicate the need for further improvements.