# AUGER: Automatically Generating Review Comments with Pre-training Models

arXiv: https://arxiv.org/abs/2208.08014 · HTML: https://mlsanity.com/paper/2208.08014/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2022.

## Built on by (most cited first, 23 of 23)

- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [LLM Critics Help Catch LLM Bugs](https://mlsanity.com/paper/2407.00215/) (2024)
- [LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2308.11148/) (2023)
- [Automatic Programming: Large Language Models and Beyond](https://mlsanity.com/paper/2405.02213/) (2024)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation](https://mlsanity.com/paper/2411.10129/) (2024)
- [Combining Large Language Models with Static Analyzers for Code Review Generation](https://mlsanity.com/paper/2502.06633/) (2025)
- [Retrieval-Augmented Code Review Comment Generation](https://mlsanity.com/paper/2506.11591/) (2025)
- [Understanding Dominant Themes in Reviewing Agentic AI-authored Code](https://mlsanity.com/paper/2601.19287/) (2026)
- [SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review](https://mlsanity.com/paper/2607.06065/) (2026)
- [Leveraging Reviewer Experience in Code Review Comment Generation](https://mlsanity.com/paper/2409.10959/) (2024)
- [Issue-Oriented Agent-Based Framework for Automated Review Comment Generation](https://mlsanity.com/paper/2511.00517/) (2025)
- [Benchmarking LLMs for Fine-Grained Code Review with Enriched Context in Practice](https://mlsanity.com/paper/2511.07017/) (2025)
- [Towards Practical Defect-Focused Automated Code Review](https://mlsanity.com/paper/2505.17928/) (2025)
- [When More Retrieval Hurts: Retrieval-Augmented Code Review Generation](https://mlsanity.com/paper/2511.05302/) (2025)
- [Automatic Detection of LLM-Generated Code: A Comparative Case Study of Contemporary Models Across Function and Class Granularities](https://mlsanity.com/paper/2409.01382/) (2024)
- [Previously on... Automating Code Review](https://mlsanity.com/paper/2508.18003/) (2025)
- [Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review](https://mlsanity.com/paper/2605.17548/) (2026)
- [Improving Automated Secure Code Reviews: A Synthetic Dataset for Code Vulnerability Flaws](https://mlsanity.com/paper/2504.16310/) (2025)
- [Fine-Tuning Multilingual Language Models for Code Review: An Empirical Study on Industrial C# Projects](https://mlsanity.com/paper/2507.19271/) (2025)
- [A Note on Code Quality Score: LLMs for Maintainable Large Codebases](https://mlsanity.com/paper/2508.02732/) (2025)
- [XSearch: Explainable Code Search via Concept-to-Code Alignment](https://mlsanity.com/paper/2605.16046/) (2026)

## Abstract (arXiv)

Code review is one of the best practices as a powerful safeguard for software quality. In practice, senior or highly skilled reviewers inspect source code and provide constructive comments, considering what authors may ignore, for example, some special cases. The collaborative validation between contributors results in code being highly qualified and less chance of bugs. However, since personal knowledge is limited and varies, the efficiency and effectiveness of code review practice are worthy of further improvement. In fact, it still takes a colossal and time-consuming effort to deliver useful review comments. This paper explores a synergy of multiple practical review comments to enhance code review and proposes AUGER (AUtomatically GEnerating Review comments): a review comments generator with pre-training models. We first collect empirical review data from 11 notable Java projects and construct a dataset of 10,882 code changes. By leveraging Text-to-Text Transfer Transformer (T5) models, the framework synthesizes valuable knowledge in the training stage and effectively outperforms baselines by 37.38% in ROUGE-L. 29% of our automatic review comments are considered useful according to prior studies. The inference generates just in 20 seconds and is also open to training further. Moreover, the performance also gets improved when thoroughly analyzed in case study.