通过逐步融合代码与文本，提升漏洞报告摘要的准确性和完整性。
Progressive Code Integration for Abstractive Bug Report Summarization
- 逐步引入长代码片段，突破大模型上下文限制。
- 在四个数据集上相较抽取式方法提升7.5%-58.2%。
- 适合需要精准理解缺陷的开发者和自动化诊断系统使用。
漏洞报告通常结构松散且冗长，给开发者高效理解软件问题带来挑战。现有摘要方法多依赖表层文本特征，导致摘要不完整或重复，且常忽略关联的代码片段——而代码对准确缺陷诊断至关重要。为此，我们提出一种面向大语言模型的渐进式代码融合框架，用于抽象型漏洞报告摘要生成。该方法将长代码片段分步融入文本内容，克服标准大模型上下文窗口限制，生成语义丰富的摘要。在四个基准数据集上使用八种大语言模型评估，该流程相比抽取式基线提升7.5%-58.2%，性能接近当前最优抽象方法，验证了联合利用文本与代码信息对提升漏洞理解的有效性。
原文摘要 · Abstract (English)
Bug reports are often unstructured and verbose, making it challenging for developers to efficiently comprehend software issues. Existing summarization approaches typically rely on surface-level textual cues, resulting in incomplete or redundant summaries, and they frequently ignore associated code snippets, which are essential for accurate defect diagnosis. To address these limitations, we propose a progressive code-integration framework for LLM-based abstractive bug report summarization. Our approach incrementally incorporates long code snippets alongside textual content, overcoming standard LLM context window constraints and producing semantically rich summaries. Evaluated on four benchmark datasets using eight LLMs, our pipeline outperforms extractive baselines by 7.5%-58.2% and achieves performance comparable to state-of-the-art abstractive methods, highlighting the benefits of jointly leveraging textual and code information for enhanced bug comprehension.
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。