English

Automated Bug Triaging using Instruction-Tuned Large Language Models

Software Engineering 2025-09-01 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2508.21156,
  title  = {Automated Bug Triaging using Instruction-Tuned Large Language Models},
  author = {Kiana Kiashemshaki and Arsham Khosravani and Alireza Hosseinpour and Arshia Akhavan},
  journal= {arXiv preprint arXiv:2508.21156},
  year   = {2025}
}

Comments

11 pages, 7 figures

R2 v1 2026-07-01T05:11:02.946Z