Exploring the Potential of Large Language Models to Generate Formative Programming Feedback
This work addresses the problem of providing automated feedback for novice programmers, but it is incremental as it builds on existing research into LLMs for programming tasks.
The study explored using ChatGPT to generate formative feedback on introductory programming tasks, finding it performs reasonably well for some tasks and errors, potentially benefiting students, but noted it can provide misleading information requiring educator guidance.
Ever since the emergence of large language models (LLMs) and related applications, such as ChatGPT, its performance and error analysis for programming tasks have been subject to research. In this work-in-progress paper, we explore the potential of such LLMs for computing educators and learners, as we analyze the feedback it generates to a given input containing program code. In particular, we aim at (1) exploring how an LLM like ChatGPT responds to students seeking help with their introductory programming tasks, and (2) identifying feedback types in its responses. To achieve these goals, we used students' programming sequences from a dataset gathered within a CS1 course as input for ChatGPT along with questions required to elicit feedback and correct solutions. The results show that ChatGPT performs reasonably well for some of the introductory programming tasks and student errors, which means that students can potentially benefit. However, educators should provide guidance on how to use the provided feedback, as it can contain misleading information for novices.