用大模型自动补全缺陷报告缺失信息，提升可复现性
ImproBR: Bug Report Improver Using LLMs
- 结合小模型与大模型，分步检测并修复报告中的关键信息缺失
- 在真实数据上将可执行复现步骤比例从28.8%提升至67.6%
- 适合需要自动化处理用户提交缺陷报告的开发团队使用
缺陷追踪系统在软件维护中至关重要，但开发者常面临用户提交的报告质量低下问题，缺少如复现步骤（S2R）、观察行为（OB）和预期行为（EB）等关键信息。我们提出ImproBR，一种基于大模型的流水线方法，可自动检测并改进缺陷报告中缺失、不完整或模糊的S2R、OB和EB部分。ImproBR采用混合检测器，结合微调后的DistilBERT、启发式分析与大模型分析，由GPT-4o mini通过特定段落的少量示例提示引导，并利用基于Minecraft Wiki领域知识的检索增强生成（RAG）管道。在Mojira数据集上的评估显示，ImproBR将结构完整性从7.9%提升至96.4%，可执行复现步骤比例超过两倍增长（从28.8%升至67.6%），完全可复现的缺陷报告数量从1例增至13例，涵盖139个具有挑战性的实际报告。
原文摘要 · Abstract (English)
Bug tracking systems play a crucial role in software maintenance, yet developers frequently struggle with low-quality user-submitted reports that omit essential details such as Steps to Reproduce (S2R), Observed Behavior (OB), and Expected Behavior (EB). We propose ImproBR, an LLM-based pipeline that automatically detects and improves bug reports by addressing missing, incomplete, and ambiguous S2R, OB, and EB sections. ImproBR employs a hybrid detector combining fine-tuned DistilBERT, heuristic analysis, and an LLM analyzer, guided by GPT-4o mini with section-specific few-shot prompts and a Retrieval-Augmented Generation (RAG) pipeline grounded in Minecraft Wiki domain knowledge. Evaluated on Mojira, ImproBR improved structural completeness from 7.9% to 96.4%, more than doubled the proportion of executable S2R from 28.8% to 67.6%, and raised fully reproducible bug reports from 1 to 13 across 139 challenging real-world reports.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。