# Combining Large Language Models with Static Analyzers for Code Review Generation

arXiv: https://arxiv.org/abs/2502.06633 · HTML: https://mlsanity.com/paper/2502.06633/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 61 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Builds on (most cited first, 30 of 30)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [Automating Code Review Activities by Large-Scale Pre-training](https://mlsanity.com/paper/2203.09095/) (2022)
- [No More Manual Tests? Evaluating and Improving ChatGPT for Unit Test Generation](https://mlsanity.com/paper/2305.04207/) (2023)
- [GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis](https://mlsanity.com/paper/2308.03314/) (2023)
- [Using Pre-Trained Models to Boost Code Review Automation](https://mlsanity.com/paper/2201.06850/) (2022)
- [CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences](https://mlsanity.com/paper/2403.09032/) (2024)
- [Towards Automating Code Review Activities](https://mlsanity.com/paper/2101.02518/) (2021)
- [D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis](https://mlsanity.com/paper/2102.07995/) (2021)
- [LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2308.11148/) (2023)
- [ReposVul: A Repository-Level High-Quality Vulnerability Dataset](https://mlsanity.com/paper/2401.13169/) (2024)
- [Learning Deep Semantics for Test Completion](https://mlsanity.com/paper/2302.10166/) (2023)
- [AUGER: Automatically Generating Review Comments with Pre-training Models](https://mlsanity.com/paper/2208.08014/) (2022)
- [STALL+: Boosting LLM-based Repository-level Code Completion with Static Analysis](https://mlsanity.com/paper/2406.10018/) (2024)
- [Code Review Automation: Strengths and Weaknesses of the State of the Art](https://mlsanity.com/paper/2401.05136/) (2024)
- [CORE: Automating Review Recommendation for Code Changes](https://mlsanity.com/paper/1912.09652/) (2019)
- [PyTy: Repairing Static Type Errors in Python](https://mlsanity.com/paper/2401.06619/) (2024)
- [The Effectiveness of Supervised Machine Learning Algorithms in Predicting Software Refactoring](https://mlsanity.com/paper/2001.03338/) (2020)
- [A Critical Comparison on Six Static Analysis Tools: Detection, Agreement, and Precision](https://mlsanity.com/paper/2101.08832/) (2021)
- [Improving the Learning of Code Review Successive Tasks with Cross-Task Knowledge Distillation](https://mlsanity.com/paper/2402.02063/) (2024)
- [SkipAnalyzer: A Tool for Static Code Analysis with Large Language Models](https://mlsanity.com/paper/2310.18532/) (2023)
- [A Roadmap on Modern Code Review: Challenges and Opportunities](https://mlsanity.com/paper/2405.18216/) (2024)

## Built on by (most cited first, 6 of 6)

- [Repairing vulnerabilities without invisible hands. A differentiated replication study on LLMs](https://mlsanity.com/paper/2507.20977/) (2025)
- [Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review](https://mlsanity.com/paper/2605.17548/) (2026)
- [MetaLint: Easy-to-Hard Generalization for Code Linting](https://mlsanity.com/paper/2507.11687/) (2025)
- [Enhancing Debugging Skills with AI-Powered Assistance: A Real-Time Tool for Debugging Support](https://mlsanity.com/paper/2601.02504/) (2026)
- [FlowArk: Boosting Agentic Data-flow Analysis for Android Apps via Context-Aware Knowledge Reuse](https://mlsanity.com/paper/2607.11308/) (2026)
- [Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy](https://mlsanity.com/paper/2607.21677/) (2026)

## Abstract (arXiv)

Code review is a crucial but often complex, subjective, and time-consuming activity in software development. Over the past decades, significant efforts have been made to automate this process. Early approaches focused on knowledge-based systems (KBS) that apply rule-based mechanisms to detect code issues, providing precise feedback but struggling with complex, context-dependent cases. More recent work has shifted toward fine-tuning pre-trained language models for code review, enabling broader issue coverage but often at the expense of precision. In this paper, we propose a hybrid approach that combines the strengths of KBS and learning-based systems (LBS) to generate high-quality, comprehensive code reviews. Our method integrates knowledge at three distinct stages of the language model pipeline: during data preparation (Data-Augmented Training, DAT), at inference (Retrieval-Augmented Generation, RAG), and after inference (Naive Concatenation of Outputs, NCO). We empirically evaluate our combination strategies against standalone KBS and LBS fine-tuned on a real-world dataset. Our results show that these hybrid strategies enhance the relevance, completeness, and overall quality of review comments, effectively bridging the gap between rule-based tools and deep learning models.