.png){kind=icon}
Return
Leveraging Large Language Models for Software Defect Detection
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-04200-2_9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper evaluates Large Language Models (LLMs) for static code analysis and defect detection across test sets of increasing complexity. Our findings show LLMs excel with smaller code fragments but deteriorate with increasing complexity. While inconsistent with larger codebases, LLMs provide valuable insights on readability, security, and maintainability that traditional tools miss. We identify key advantages and limitations, concluding that LLMs serve best as complementary solutions to conventional tools, with unique strengths in understanding developer intent and providing contextual recommendations for smaller code units.
Keywords:
Large language models
Software defect detection
Static code analysis
Software quality assurance
Journal
S
IF:
0
Papers:
29
Citations:
0
Organization
Cited Papers
ShareSave
ShareSaveShareSaveSoftware Vulnerability Detection Using Deep Neural Networks: A Survey.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
ShareSave
View more