EUVIMEDEUVIMED entdecken
Crossref

Fine-Tuning Large Language Models to Improve Accuracy and Comprehensibility of Automated Code Review

Yongda Yu, Guoping Rong, Haifeng Shen, He Zhang, Dong Shao, Min Wang, Zhao Wei, Yong Xu, Juhong Wang

ACM Transactions on Software Engineering and Methodology · 31.01.2025 · 34 (1) · 1-26

DOI: 10.1145/3695993 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 27.12.2024. Verfasst von Yongda Yu und 8 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 65 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As code review is a tedious and costly software quality practice, researchers have proposed several machine learning-based methods to automate the process. The primary focus has been on accuracy, that is, how accurately the algorithms are able to detect issues in the code under review. However, human intervention still remains inevitable since results produced by automated code review are not 100% correct. To assist human reviewers in making their final decisions on automatically generated review comments, the comprehensibility of the comments underpinned by accurate localization and relevant explanations for the detected issues with repair suggestions is paramount. However, this has largely been neglected in the existing research. Large language models (LLMs) have the potential to generate code review comments that are more readable and comprehensible by humans, thanks to their remarkable processing and reasoning capabilities. However, even mainstream LLMs perform poorly in detecting the presence of code issues because they have not been specifically trained for this binary classification task required in code review. In this article, we contribute Comprehensibility of Automated Code Review using Large Language Models ( Carllm ), a novel fine-tuned LLM that has the ability to improve not only the accuracy but, more importantly, the comprehensibility of automated code review, as compared to state-of-the-art pre-trained models and general LLMs.

Zitieren

APA

Yu, Y., Rong, G., Shen, H., Zhang, H., Shao, D., Wang, M., Wei, Z., Xu, Y., & Wang, J. (2025). Fine-Tuning Large Language Models to Improve Accuracy and Comprehensibility of Automated Code Review. ACM Transactions on Software Engineering and Methodology, 34(1), 1-26. https://doi.org/10.1145/3695993

Vancouver

Yu Y, Rong G, Shen H, Zhang H, Shao D, Wang M, et al. Fine-Tuning Large Language Models to Improve Accuracy and Comprehensibility of Automated Code Review. ACM Transactions on Software Engineering and Methodology. 2025;34(1):1-26. doi:10.1145/3695993

BibTeX
@article{Yu2025,
  author = {Yu, Yongda and Rong, Guoping and Shen, Haifeng and Zhang, He and Shao, Dong and Wang, Min and Wei, Zhao and Xu, Yong and Wang, Juhong},
  title = {Fine-Tuning Large Language Models to Improve Accuracy and Comprehensibility of Automated Code Review},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2025},
  volume = {34},
  number = {1},
  pages = {1--26},
  doi = {10.1145/3695993}
}
Kostenlos starten →