LAURA: Enhancing Code Review Generation with Context-Enriched Retrieval-Augmented LLM
By: Yuxin Zhang , Yuxia Zhang , Zeyu Sun and more
Potential Business Impact:
Helps computers write better code suggestions.
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.
Similar Papers
Automated Code Review Using Large Language Models with Symbolic Reasoning
Software Engineering
AI finds coding mistakes better by thinking logically.
Operationalizing Large Language Models with Design-Aware Contexts for Code Comment Generation
Software Engineering
Helps computers write better explanations for code.
Exploring the Potential of Large Language Models in Fine-Grained Review Comment Classification
Software Engineering
Helps computers understand code feedback better.