Automated Bug Triaging using Instruction-Tuned Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kiashemshaki, Kiana, Khosravani, Arsham, Hosseinpour, Alireza, Akhavan, Arshia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916924869312512
author Kiashemshaki, Kiana
Khosravani, Arsham
Hosseinpour, Alireza
Akhavan, Arshia
author_facet Kiashemshaki, Kiana
Khosravani, Arsham
Hosseinpour, Alireza
Akhavan, Arshia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_21156
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automated Bug Triaging using Instruction-Tuned Large Language Models
Kiashemshaki, Kiana
Khosravani, Arsham
Hosseinpour, Alireza
Akhavan, Arshia
Software Engineering
D.2.7; I.2.7; I.2.6
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.
title Automated Bug Triaging using Instruction-Tuned Large Language Models
topic Software Engineering
D.2.7; I.2.7; I.2.6
url https://arxiv.org/abs/2508.21156