English

Evaluating the Quality of Code Comments Generated by Large Language Models for Novice Programmers

Software Engineering 2024-09-24 v1 Artificial Intelligence Human-Computer Interaction

Abstract

Large Language Models (LLMs) show promise in generating code comments for novice programmers, but their educational effectiveness remains under-evaluated. This study assesses the instructional quality of code comments produced by GPT-4, GPT-3.5-Turbo, and Llama2, compared to expert-developed comments, focusing on their suitability for novices. Analyzing a dataset of ``easy'' level Java solutions from LeetCode, we find that GPT-4 exhibits comparable quality to expert comments in aspects critical for beginners, such as clarity, beginner-friendliness, concept elucidation, and step-by-step guidance. GPT-4 outperforms Llama2 in discussing complexity (chi-square = 11.40, p = 0.001) and is perceived as significantly more supportive for beginners than GPT-3.5 and Llama2 with Mann-Whitney U-statistics = 300.5 and 322.5, p = 0.0017 and 0.0003). This study highlights the potential of LLMs for generating code comments tailored to novice programmers.

Keywords

Cite

@article{arxiv.2409.14368,
  title  = {Evaluating the Quality of Code Comments Generated by Large Language Models for Novice Programmers},
  author = {Aysa Xuemo Fan and Arun Balajiee Lekshmi Narayanan and Mohammad Hassany and Jiaze Ke},
  journal= {arXiv preprint arXiv:2409.14368},
  year   = {2024}
}
R2 v1 2026-06-28T18:52:45.542Z