New
How Researchers Use and Verify AI Coding Assistants: Tasks and Validation Practices in Scientific Programming
2026 · 0 citations
Generative AI has entered research programming, yet there is little evidence about which tasks researchers hand to it or how they decide whether its code is correct. We draw on 527 free-text responses to a 2025 survey of researchers who write code, most of them at U.S. universities. In each response, a researcher recounts a single task from their own work, the way they used an AI tool for it, and what they did to assess the result. We coded the task and the evaluation strategies reported, and re…
Read full paper →
Linked
LLMs for Defect Prediction in Evolving Datasets: Emerging Results and Future Directions
2025 · 3 citations
Software evolves rapidly, making it challenging for defect prediction models to remain effective without frequent retraining. While the Large Language Models (LLMs) have been widely used in SE tasks, their application to evolving datasets for quality assurance, particularly defect prediction, remains under-explored. This study investigates the use of dynamic fine-tuning techniques to enable LLMs to predict defective modules in the face of codebase evolution. We begin our study by curating datase…
Read full paper →