9 papers
Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review
Hüseyin Ãzgür Kamalı, Erdem Tuna, Vahid Haratian +1
Code review has evolved for decades, from informal peer checking to today's pull request (PR) workflows, yet it remains a largely manual and cognitively demanding process. The rise…
PR-Aware Automated Unit Test Generation: Challenges and Opportunities
Vahid Haratian, Atakan Akar, Berk Ãakar +1
Automated test generation has a substantial body of work, yet most studies focus on generating tests for complete software units, such as classes, and rely on metrics such as code…
Automated Classification of Human Code Review Comments with Large Language Models
Semih ÃaÄlar, Åükrü Eren Gökırmak, Eray Tüzün
Context: Code reviews are essential for maintaining software quality, yet many human review comments suffer from issues such as redundancy, vagueness, or lack of constructiveness.…
SERSEM: Selective Entropy-Weighted Scoring for Membership Inference in Code Language Models
Kıvanç Kuzey Dikici, Serdar Kara, Semih ÃaÄlar +2
As Large Language Models (LLMs) for code increasingly utilize massive, often non-permissively licensed datasets, evaluating data contamination through Membership Inference Attacks…
Towards Automated Detection of Inline Code Comment Smells
Ipek Oztas, U Boran Torun, Eray Tüzün
Code comments are important in software development because they directly influence software maintainability and overall quality. Bad practices of code comments lead to code commen…
Evaluating Large Language Models for Code Review
Umut Cihan, Arda İçöz, Vahid Haratian +1
Context: Code reviews are crucial for software quality. Recent AI advances have allowed large language models (LLMs) to review and fix code; now, there are tools that perform these…