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

TL;DR

LAURA is a novel framework that enhances code review comment generation by integrating context-aware retrieval and systematic guidance, significantly outperforming existing methods in accuracy and helpfulness.

Contribution

This paper introduces LAURA, a context-enriched retrieval-augmented LLM framework for code review generation, and constructs a high-quality dataset to improve review comment quality.

Findings

LAURA achieves 42.2% and 40.4% correct/helpful review comment rates.

All components of LAURA positively impact review quality.

LAURA significantly outperforms state-of-the-art baselines.

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.