Distilling Desired Comments for Enhanced Code Review with Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yu, Yongda, Zhang, Lei, Rong, Guoping, Shen, Haifeng, Zhang, Jiahao, Yan, Haoxiang, Shi, Guohao, Shao, Dong, Pan, Ruiqi, Li, Yuan, Wang, Qiushi, Tian, Zhao
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910773406597120
author Yu, Yongda
Zhang, Lei
Rong, Guoping
Shen, Haifeng
Zhang, Jiahao
Yan, Haoxiang
Shi, Guohao
Shao, Dong
Pan, Ruiqi
Li, Yuan
Wang, Qiushi
Tian, Zhao
author_facet Yu, Yongda
Zhang, Lei
Rong, Guoping
Shen, Haifeng
Zhang, Jiahao
Yan, Haoxiang
Shi, Guohao
Shao, Dong
Pan, Ruiqi
Li, Yuan
Wang, Qiushi
Tian, Zhao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20340
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Distilling Desired Comments for Enhanced Code Review with Large Language Models
Yu, Yongda
Zhang, Lei
Rong, Guoping
Shen, Haifeng
Zhang, Jiahao
Yan, Haoxiang
Shi, Guohao
Shao, Dong
Pan, Ruiqi
Li, Yuan
Wang, Qiushi
Tian, Zhao
Software Engineering
Artificial Intelligence
D.2.3; I.2.7
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.
title Distilling Desired Comments for Enhanced Code Review with Large Language Models
topic Software Engineering
Artificial Intelligence
D.2.3; I.2.7
url https://arxiv.org/abs/2412.20340