From the 1 of 2 linked papers with an AI index.
2 papers
cs.SE2026
Rethinking Training Data for Generating Code Review Comments
Leonardo Centellas-Claros, Estefania Pakarati-Cofre, Juan Pablo Sandoval Alcocer +1
The paper examines why automatically generated code review comments often lack usefulness, identifying misaligned training examples in a common dataset and proposing a taxonomy of…
cs.SE2025
Improving Automated Secure Code Reviews: A Synthetic Dataset for Code Vulnerability Flaws
Leonardo Centellas-Claros, Juan J. Alonso-Lecaros, Juan Pablo Sandoval Alcocer +1
Automation of code reviews using AI models has garnered substantial attention in the software engineering community as a strategy to reduce the cost and effort associated with trad…