2025/08/28 by Kiana Kiashemshaki, Kiashemshaki, Kiana, Arsham Khosravani +5 · 1 voice
Computer Science · #D.2.7 #Decoding methods #FOS: Computer and information sciences #Feature (linguistics) #Feature engineering #I.2.6 #I.2.7 #Language model #Quality (philosophy) #Software Engineering (cs.SE) #Software Engineering Research #Software Engineering Techniques and Practices #Task (project management) #Topic Modeling #cs.SE
paper · pdf · doi:10.48550/arxiv.2508.21156
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/08/28 · arxiv published 2025/08/28 · arxiv updated 2025/08/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Bug triaging, the task of assigning new issues to developers, is often slow and inconsistent in large projects. We present a lightweight framework that instruction-tuned large language model (LLM) with LoRA adapters and uses candidate-constrained decoding to ensure valid assignments. Tested on EclipseJDT and Mozilla datasets, the model achieves strong shortlist quality (Hit at 10 up to 0.753) despite modest exact Top-1 accuracy. On recent snapshots, accuracy rises sharply, showing the framework's potential for real-world, human-in-the-loop triaging. Our results suggest that instruction-tuned LLMs offer a practical alternative to costly feature engineering and graph-based methods.