An exploratory study on LLM-generated code and comments in code repositories
Authors:
- Yongyi JiYJYongyi Ji
- Jiaji WangJWJiaji Wang
- Yi ZhouYZYi Zhou
- Fuxiang ChenFCFuxiang Chen
- Hongji YangHYHongji Yang
Open Access
- 7 July 2026
- journal article
- Published by Elsevier in Journal of Systems and Software
- Vol. 242
Abstract
No abstract availableFunding Information
- Engineering and Physical Sciences Research Council (EP/T022108/1)
This publication has 21 references indexed in Scilit:
- Bugs in large language models generated code: an empirical studyEmpirical Software Engineering, 2025
- Using AI-based coding assistants in practice: State of affairs, perceptions, and ways forwardInformation and Software Technology, 2024
- A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges2024
- Grounded Copilot: How Programmers Interact with Code-Generating ModelsProceedings of the ACM on Programming Languages, 2023
- Few-shot training LLMs for project-specific code-summarization2022
- Is GitHub copilot a substitute for human pair-programming?2022
- Trade-offs for Substituting a Human with an Agent in a Pair Programming Context: The Good, the Bad, and the Ugly2021
- Defects4J: a database of existing faults to enable controlled testing studies for Java programs2014
- CCFinder: a multilinguistic token-based code clone detection system for large scale source codeIEEE Transactions on Software Engineering, 2002
- How Good Is That Agreement?Epidemiology, 1996