用大模型自动分配软件问题，准确率远超传统方法。
LIA: Supervised Fine-Tuning of Large Language Models for Automatic Issue Assignment
- 用大模型微调生成开发者推荐列表，基于历史任务模式匹配。
- 在Hit@1指标上提升超187.8%，最高比基线高211.2%。
- 适合开源项目维护团队快速分配新提交的问题。
问题分配是软件维护中的关键环节，需将新报告的问题指派给合适的开发人员。人工分配易出错且不一致，尤其在每月报告数千个问题的大规模开源项目中。现有自动化方法多依赖大量特定项目训练数据或稀疏嘈杂的关系信息，效果受限。为此，本文提出LIA（基于大语言模型的问题分配），采用监督微调方式，适配DeepSeek-R1-Distill-Llama-8B模型，直接从问题标题与描述生成开发者排名建议。该模型利用预训练语言模型对自然语言及软件文本的语义理解能力，结合历史问题-开发者分配模式，推断最可能处理新问题的开发者。全面评估显示，LIA在多个指标上显著优于其基础模型及当前主流方法：相比DeepSeek-R1-Distill-Llama-8B，Hit@1最高提升187.8%；相较四种领先方法，最高提升达211.2%。结果表明，领域适配的大语言模型在软件维护任务中具有强大潜力，LIA可作为高效实用的问题分配方案。
原文摘要 · Abstract (English)
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.
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。