跳到主要导航 跳到搜索 跳到主要内容

LAURA: Enhancing Code Review Generation with Context-Enriched Retrieval-Augmented LLM

  • Yuxin Zhang
  • , Yuxia Zhang*
  • , Zeyu Sun
  • , Yanjie Jiang
  • , Hui Liu
  • *此作品的通讯作者
  • Beijing Institute of Technology
  • CAS - Institute of Software
  • Tianjin University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Code review is critical for ensuring software quality and maintainability. With the rapid growth in software scale and complexity, code review has become a bottleneck in the development process because of its time-consuming and knowledge-intensive nature and the shortage of experienced developers willing to review code. Several approaches have been proposed for automatically generating code reviews based on retrieval, neural machine translation, pre-trained models, or large language models (LLMs). These approaches mainly leverage historical code changes and review comments. However, a large amount of crucial information for code review, such as the context of code changes and prior review knowledge, has been overlooked. This paper proposes an LLM-based review knowledge-augmented, context-aware framework for code review generation, named LAURA. The framework integrates review exemplar retrieval, context augmentation, and systematic guidance to enhance the performance of ChatGPT-4o and DeepSeek v3 in generating code review comments. Besides, given the extensive low-quality reviews in existing datasets, we also constructed a high-quality dataset. Experimental results show that for both models, LAURA generates review comments that are either completely correct or at least helpful to developers in 42.2% and 40.4% of cases, respectively, significantly outperforming SOTA baselines. Furthermore, our ablation studies demonstrate that all components of LAURA contribute positively to improving comment quality.

源语言英语
主期刊名Proceedings - 2025 40th IEEE/ACM International Conference on Automated Software Engineering, ASE 2025
出版商Institute of Electrical and Electronics Engineers Inc.
2983-2995
页数13
ISBN(电子版)9798350357332
DOI
出版状态已出版 - 2025
已对外发布
活动2025 40th IEEE/ACM International Conference on Automated Software Engineering, ASE 2025 - Seoul, 韩国
期限: 16 11月 202520 11月 2025

出版系列

姓名Proceedings - 2025 40th IEEE/ACM International Conference on Automated Software Engineering, ASE 2025

会议

会议2025 40th IEEE/ACM International Conference on Automated Software Engineering, ASE 2025
国家/地区韩国
Seoul
时期16/11/2520/11/25

指纹

探究 'LAURA: Enhancing Code Review Generation with Context-Enriched Retrieval-Augmented LLM' 的科研主题。它们共同构成独一无二的指纹。

引用此