.png){kind=icon}
.png){kind=icon}
Return
CoRaCMG: Contextual retrieval-augmented framework for commit message generation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.infsof.2026.108169.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In software development and maintenance, commit messages play a key role in documenting the intent behind code changes, supporting collaboration, review, and maintenance. However, they are often low-quality, vague, or incomplete, limiting their usefulness. Commit Message Generation (CMG) aims to automatically generate descriptive commit messages from code diffs to reduce developers’ effort and improve message quality. Although recent advances in Large Language Models (LLMs) have shown promise in automating CMG, their performance remains limited.
Keywords:
Commit Message Generation
Large Language Models
Code Diffs
Contextual Retrieval
Software Maintenance
Journal
IF:
4.3
Papers:
3.7K
Citations:
7.7K
Organization
No organization information available