4 papers
Historian: Reducing Manual Validation in APR Benchmarking via Evidence-Based Assessment
Sahand Moslemi, Mayasah Lami, Anil Koyuncu
Assessing the correctness of patches generated by Automated Program Repair (APR) is a major bottleneck. Manual validation is labor-intensive and limited: exact matching overlooks v…
Are We SOLID Yet? An Empirical Study on Prompting LLMs to Detect Design Principle Violations
Fatih Pehlivan, Arçin Ãlkü Ergüzen, Sahand Moslemi Yengejeh +2
Traditional static analysis methods struggle to detect semantic design flaws, such as violations of the SOLID principles, which require a strong understanding of object-oriented de…
LLMShot: Reducing snapshot testing maintenance via LLMs
Ergün Batuhan Kaynak, Mayasah Lami, Sahand Moslemi +1
Snapshot testing has emerged as a critical technique for UI validation in modern software development, yet it suffers from substantial maintenance overhead due to frequent UI chang…
Explicit Vulnerability Generation with LLMs: An Investigation Beyond Adversarial Attacks
Emir Bosnak, Sahand Moslemi, Mayasah Lami +1
Large Language Models (LLMs) are increasingly used as code assistants, yet their behavior when explicitly asked to generate insecure code remains poorly understood. While prior res…