用用户编辑次数评估提交消息生成，发现编辑距离比传统指标更贴近真实体验。
Towards Realistic Evaluation of Commit Message Generation by Matching Online and Offline Settings
- 用用户实际编辑次数作为在线评价标准，反向筛选适合的离线评估指标。
- 在656对数据上验证，编辑距离与真实用户行为相关性最高。
- 开源了工具、数据集和代码，支持后续可复现的生成评估研究。
当提交消息生成（CMG）系统集成至JetBrains的IDE等产品时，我们通过用户对生成消息的接受程度进行在线评估。然而，每次迭代都需影响真实用户并等待足够统计量，难以频繁开展。相比之下，研究中常用的离线评估虽快速，但依赖自动指标，未必反映真实用户偏好。本文提出一种新方法：利用在线指标——用户在提交前对生成消息的编辑次数——来筛选适合的离线评估指标。为此，我们开发了一款模拟真实工作流的标记收集工具，收集了57组由GPT-4生成、经人类专家编辑的提交消息对，并设计并验证了合成扩展方法。最终构建包含656对数据的基准集，研究常用相似度指标与在线指标的相关性。结果表明，编辑距离与在线指标相关性最高，而常用指标如BLEU、METEOR相关性较低。这与以往基于人工标注的研究结论相反，说明真实用户交互与受控环境下人工评分存在显著差异。所有代码与数据集已公开：https://jb.gg/cmg-evaluation。
原文摘要 · Abstract (English)
When a Commit Message Generation (CMG) system is integrated into the IDEs and other products at JetBrains, we perform online evaluation based on user acceptance of the generated messages. However, performing online experiments with every change to a CMG system is troublesome, as each iteration affects users and requires time to collect enough statistics. On the other hand, offline evaluation, a prevalent approach in the research literature, facilitates fast experiments but employs automatic metrics that are not guaranteed to represent the preferences of real users. In this work, we describe a novel way we employed to deal with this problem at JetBrains, by leveraging an online metric - the number of edits users introduce before committing the generated messages to the VCS - to select metrics for offline experiments. To support this new type of evaluation, we develop a novel markup collection tool mimicking the real workflow with a CMG system, collect a dataset with 57 pairs consisting of commit messages generated by GPT-4 and their counterparts edited by human experts, and design and verify a way to synthetically extend such a dataset. Then, we use the final dataset of 656 pairs to study how the widely used similarity metrics correlate with the online metric reflecting the real users' experience. Our results indicate that edit distance exhibits the highest correlation with the online metric, whereas commonly used similarity metrics such as BLEU and METEOR demonstrate low correlation. This contradicts the previous studies on similarity metrics for CMG, suggesting that user interactions with a CMG system in real-world settings differ significantly from the responses by human labelers within controlled environments. We release all the code and the dataset to support future research in the field: https://jb.gg/cmg-evaluation.
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。