arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.01780cs.SEcs.AI
收藏

LIA:大型语言模型的监督微调用于自动问题分配

LIA: Supervised Fine-Tuning of Large Language Models for Automatic Issue Assignment

California State University Northridge(加州州立大学北岭分校);Bowling Green State University(鲍灵格林州立大学)

Arsham Khosravani, Alireza Hoseinpour, Arshia Akhavan, Mehdi Keshani, Abbas Heydarnoori

AI总结:

LIA通过监督微调大型语言模型,实现高效准确的问题分配,显著优于现有方法。

摘要:

问题分配是软件维护中的关键过程,其中新的问题报告会被验证并分配给合适的开发人员。然而,手动问题分配往往不一致且容易出错,尤其是在大型开源项目中,每月会报告数千个新问题。现有的自动化方法已显示出潜力,但许多方法依赖大量的项目特定训练数据或关系信息,这些信息通常稀疏且嘈杂,限制了其有效性。为了解决这些挑战,我们提出了LIA(基于LLM的问题分配),它利用监督微调来适应一个大型语言模型,即DeepSeek-R1-Distill-Llama-8B。通过利用LLM对自然语言和软件相关文本的预训练语义理解,LIA学会直接从问题标题和描述中生成排序的开发人员推荐。排序基于模型对历史问题到开发人员分配的了解,利用过去任务中的模式来推断哪些开发人员最有可能处理新问题。通过全面的评估,我们证明LIA在基线预训练模型和最先进的基线方法上都取得了显著改进。它在Hit@1指标上比DeepSeek-R1-Distill-Llama-8B预训练基线模型高187.8%,并在四个领先的问题分配方法上以Hit@1分数高出211.2%。这些结果突显了领域适应的LLM在软件维护任务中的有效性,并确立了LIA作为问题分配的实用且高性能的解决方案。

英文摘要:

Issue assignment is a critical process in software maintenance, where new issue reports are validated and assigned to suitable developers. However, manual issue assignment is often inconsistent and error-prone, especially in large open-source projects where thousands of new issues are reported monthly. Existing automated approaches have shown promise, but many rely heavily on large volumes of project-specific training data or relational information that is often sparse and noisy, which limits their effectiveness. To address these challenges, we propose LIA (LLM-based Issue Assignment), which employs supervised fine-tuning to adapt an LLM, DeepSeek-R1-Distill-Llama-8B in this work, for automatic issue assignment. By leveraging the LLM's pretrained semantic understanding of natural language and software-related text, LIA learns to generate ranked developer recommendations directly from issue titles and descriptions. The ranking is based on the model's learned understanding of historical issue-to-developer assignments, using patterns from past tasks to infer which developers are most likely to handle new issues. Through comprehensive evaluation, we show that LIA delivers substantial improvements over both its base pretrained model and state-of-the-art baselines. It achieves up to +187.8% higher Hit@1 compared to the DeepSeek-R1-Distill-Llama-8B pretrained base model, and outperforms four leading issue assignment methods by as much as +211.2% in Hit@1 score. These results highlight the effectiveness of domain-adapted LLMs for software maintenance tasks and establish LIA as a practical, high-performing solution for issue assignment.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑