Preprint
Distilling Desired Comments for Enhanced Code Review with Large Language Models
arXiv
Cornell University
29/12/2024
Metrics
1 Record Views
Abstract
There has been a growing interest in using Large Language Models (LLMs) for code review thanks to their proven proficiency in code comprehension. The primary objective of most review scenarios is to generate desired review comments (DRCs) that explicitly identify issues to trigger code fixes. However, existing LLM-based solutions are not so effective in generating DRCs for various reasons such as hallucination. To enhance their code review ability, they need to be fine-tuned with a customized dataset that is ideally full of DRCs. Nevertheless, such a dataset is not yet available, while manual annotation of DRCs is too laborious to be practical. In this paper, we propose a dataset distillation method, Desiview, which can automatically construct a distilled dataset by identifying DRCs from a code review dataset. Experiments on the CodeReviewer dataset comprising more than 150K review entries show that Desiview achieves an impressive performance of 88.93%, 80.37%, 86.67%, and 84.44% in terms of Precision, Recall, Accuracy, and F1, respectively, surpassing state-of-the-art methods. To validate the effect of such a distilled dataset on enhancing LLMs' code review ability, we first fine-tune the latest LLaMA series (i.e., LLaMA 3 and LLaMA 3.1) to build model Desiview4FT. We then enhance the model training effect through KTO alignment by feeding those review comments identified as non-DRCs to the LLMs, resulting in model Desiview4FA. Verification results indicate that Desiview4FA slightly outperforms Desiview4FT, while both models have significantly improved against the base models in terms of generating DRCs. Human evaluation confirms that both models identify issues more accurately and tend to generate review comments that better describe the issues contained in the code than the base LLMs do.
Details
- Title
- Distilling Desired Comments for Enhanced Code Review with Large Language Models
- Creators
- Yongda Yu - Nanjing UniversityLei Zhang - Nanjing UniversityGuoping Rong - Nanjing UniversityHaifeng Shen - Southern Cross UniversityJiahao Zhang - Nanjing UniversityHaoxiang Yan - Nanjing UniversityGuohao Shi - Nanjing UniversityDong Shao - Nanjing UniversityRuiqi Pan - HTCYuan Li - HTCQiushi Wang - HTCZhao Tian - HTC
- Publication Details
- arXiv
- Publisher
- Cornell University
- Number of pages
- 12
- Identifiers
- 991013245450602368
- Academic Unit
- Faculty of Science and Engineering
- Language
- English
- Resource Type
- Preprint