.png){kind=icon}
.png){kind=icon}
Return
Data augmentation of Python code refactoring datasets based on LLMs
.png){kind=icon}
OA
AI
V
R
S
DOI：10.1016/j.jss.2026.113009.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Code-level augmentation exceeds original and SMOTE in Python refactoring detection. • A pipeline for augmenting, validating, and balancing imbalanced datasets. • In-depth assessment of code embedding similarity of original and generated data. • Availability of balanced datasets with synthetically generated refactoring data. • Support for refactoring detection, prioritization, and recommendation tasks.
Keywords:
Refactoring
Artificial Intelligence
AI in software refactoring
Machine learning
Data augmentation
LLMs in software engineering
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.1
Papers:
5.4K
Citations:
8.4K
Organization
No organization information available
Cited Papers