Skip to main navigation Skip to search Skip to main content

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

  • Yuxin Zhang
  • , Yuxia Zhang*
  • , Zeyu Sun
  • , Yanjie Jiang
  • , Hui Liu
  • *Corresponding author for this work
  • Beijing Institute of Technology
  • CAS - Institute of Software
  • Tianjin University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2025 40th IEEE/ACM International Conference on Automated Software Engineering, ASE 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2983-2995
Number of pages13
ISBN (Electronic)9798350357332
DOIs
Publication statusPublished - 2025
Externally publishedYes
Event2025 40th IEEE/ACM International Conference on Automated Software Engineering, ASE 2025 - Seoul, Korea, Republic of
Duration: 16 Nov 202520 Nov 2025

Publication series

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

Conference

Conference2025 40th IEEE/ACM International Conference on Automated Software Engineering, ASE 2025
Country/TerritoryKorea, Republic of
CitySeoul
Period16/11/2520/11/25

Keywords

  • Code Review Generation
  • Context-aware
  • LLMs
  • Review Exemplar Retrieval

Fingerprint

Dive into the research topics of 'LAURA: Enhancing Code Review Generation with Context-Enriched Retrieval-Augmented LLM'. Together they form a unique fingerprint.

Cite this