发表机构
National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University（南京大学人工智能学院新型软件技术国家重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CoCoRerank提出基于组件与候选一致性的重排序框架，利用完整CCS格式监督，提升LLM生成提交信息的结构预测与主题质量。
AI 中文摘要
提交信息对于理解软件变更至关重要，然而自动提交信息生成通常将信息视为非结构化的文本序列。这限制了其支持标准化开发工作流的能力，在这些工作流中，提交信息通常期望遵循常规提交规范（CCS），形式为类型（范围）：主题。在本文中，我们研究了在完整CCS格式下的常规提交信息生成。我们构建了一个新的基准数据集，包含从开源GitHub仓库收集的86,688条高质量提交，每条信息通过结构规范化和语义质量过滤被规范化为类型、范围和主题。基于该基准，我们提出了一种名为CoCoRerank的基于二维一致性重排序框架，用于基于大语言模型的生成。CoCoRerank利用了代码变更、类型、范围和主题之间的水平一致性，以及多个生成候选之间的垂直共识。使用代表性CMG基线、LLM生成器、重排序策略和消融变体的实验表明，CoCoRerank提高了结构组件预测和主题生成质量。结果表明，完整的CCS监督和多维一致性建模为准确和标准化的提交信息生成提供了有效基础。该工件已公开发布于该https URL。
英文摘要
Commit messages are essential for understanding software changes, yet automatic commit message generation typically treats a message as an unstructured text sequence. This limits its ability to support standardized development workflows, where commit messages are often expected to follow the Conventional Commits Specification (CCS) in the form type (scope): subject. In this paper, we study conventional commit message generation under the complete CCS format. We construct a new benchmark of 86,688 high-quality commits collected from open-source GitHub repositories, with each message normalized into type, scope, and subject through structural normalization and semantic quality filtering. Based on this benchmark, we propose a two-dimensional consistency-based reranking framework named CoCoRerank for LLM-based generation. CoCoRerank exploits horizontal consistency among the code change, type, scope, and subject, as well as vertical consensus across multiple generated candidates. Experiments with representative CMG baselines, LLM generators, reranking strategies, and ablation variants show that CoCoRerank improves both structural component prediction and subject generation quality. The results demonstrate that complete CCS supervision and multidimensional consistency modeling provide an effective foundation for accurate and standardized commit message generation. The artifact is publicly released at https://github.com/bluewhalebug/CoCoRerank.
Comments14 pages, 4 figures
