Large Language Models (GPT) for automating feedback on programming assignments

TL;DR

This study explores using GPT-3.5 to generate personalized feedback for programming assignments, showing improved student performance and reduced time to solve when hints are available, with some over-reliance observed.

Contribution

It demonstrates the effectiveness of GPT-3.5 in automating personalized feedback for programming tasks, enhancing student success rates and efficiency.

Findings

GPT hints improved success rates in subsequent attempts

Students relied less on standard feedback when GPT hints were available

Over-reliance on GPT hints was observed when they were unavailable

Abstract

Addressing the challenge of generating personalized feedback for programming assignments is demanding due to several factors, like the complexity of code syntax or different ways to correctly solve a task. In this experimental study, we automated the process of feedback generation by employing OpenAI's GPT-3.5 model to generate personalized hints for students solving programming assignments on an automated assessment platform. Students rated the usefulness of GPT-generated hints positively. The experimental group (with GPT hints enabled) relied less on the platform's regular feedback but performed better in terms of percentage of successful submissions across consecutive attempts for tasks, where GPT hints were enabled. For tasks where the GPT feedback was made unavailable, the experimental group needed significantly less time to solve assignments. Furthermore, when GPT hints were unavailable, students in the experimental condition were initially less likely to solve the assignment correctly. This suggests potential over-reliance on GPT-generated feedback. However, students in the experimental condition were able to correct reasonably rapidly, reaching the same percentage correct after seven submission attempts. The availability of GPT hints did not significantly impact students' affective state.