Automated Bug Triaging using Instruction-Tuned Large Language Models
By: Kiana Kiashemshaki , Arsham Khosravani , Alireza Hosseinpour and more
Potential Business Impact:
Helps assign computer bugs to the right people faster.
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.
Similar Papers
Can We Enhance Bug Report Quality Using LLMs?: An Empirical Study of LLM-Based Bug Report Generation
Software Engineering
Makes bug reports clear for faster fixes.
Leveraging Large Language Model for Information Retrieval-based Bug Localization
Software Engineering
Finds computer code errors faster using smart language.
Large Language Models for Fault Localization: An Empirical Study
Software Engineering
Finds bugs in computer code faster.