mlsanityData to 7 Oct 2026

AI-Mediated Code Comment Improvement

arXiv 2505.09021 ↗First posted 13 May 2025cs.SE cs.AI cs.PLcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper describes an approach to improve code comments along different quality axes by rewriting those comments with customized Artificial Intelligence (AI)-based tools. We conduct an empirical study followed by grounded theory qualitative analysis to determine the quality axes to improve. Then we propose a procedure using a Large Language Model (LLM) to rewrite existing code comments along the quality axes. We implement our procedure using GPT-4o, then distil the results into a smaller model capable of being run in-house, so users can maintain data custody. We evaluate both our approach using GPT-4o and the distilled model versions. We show in an evaluation how our procedure improves code comments along the quality axes. We release all data and source code in an online repository for reproducibility.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 66 references that are in the map. First posted on arXiv 13 May 2025.

Builds on

23 of 66 references.

References · 23

  1. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  2. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  3. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  4. 2020A Transformer-based Approach for Source Code Summarizationcited by 129
  5. 2018The Adverse Effects of Code Duplication in Machine Learning Models of Codecited by 123
  6. 2020Improved Code Summarization via a Graph Neural Networkcited by 79
  7. 2019A Neural Model for Generating Natural Language Summaries of Program Subroutinescited by 76
  8. 2023Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learningcited by 71
  9. 2024Can LLMs Replace Manual Annotation of Software Engineering Artifacts?cited by 40
  10. 2019Retrieve and Refine: Exemplar-based Neural Comment Generationcited by 36
  11. 2023Distilled GPT for Source Code Summarizationcited by 30
  12. 2021Project-Level Encoding for Neural Source Code Summarization of Subroutinescited by 24
11 more
  1. 2022Are We Building on the Rock? On the Importance of Data Preprocessing for Code Summarizationcited by 22
  2. 2023Developer-Intent Driven Code Comment Generationcited by 16
  3. 2019A Survey of Automatic Generation of Source Code Comments: Algorithms and Techniquescited by 15
  4. 2021Socio-Technical Grounded Theory for Software Engineeringcited by 7
  5. 2024Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generationcited by 7
  6. 2023A Language Model of Java Methods with Train/Test Deduplicationcited by 6
  7. 2023Semantic Similarity Loss for Neural Source Code Summarizationcited by 5
  8. 2023Autonomy Is An Acquired Taste: Exploring Developer Preferences for GitHub Botscited by 4
  9. 2021Do you really code? Designing and Evaluating Screening Questions for Online Surveys with Programmerscited by 3
  10. 2022Automatic Comment Generation via Multi-Pass Deliberationcited by 3
  11. 2023Statement-based Memory for Neural Source Code Summarizationcited by 2

Built on by

Not cited yet.