# Retrieval-Augmented Code Review Comment Generation

arXiv: https://arxiv.org/abs/2506.11591 · HTML: https://mlsanity.com/paper/2506.11591/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 13 Jun 2025.

## Placed in

- Retrieval-augmented generation / [RAG for code](https://mlsanity.com/rag/rag-for-code/)

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [CodeT5+: Open Code Large Language Models for Code Understanding and Generation](https://mlsanity.com/paper/2305.07922/) (2023)
- [Retrieval Augmented Code Generation and Summarization](https://mlsanity.com/paper/2108.11601/) (2021)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [InferFix: End-to-End Program Repair with LLMs](https://mlsanity.com/paper/2303.07263/) (2023)
- [Using Pre-Trained Models to Boost Code Review Automation](https://mlsanity.com/paper/2201.06850/) (2022)
- [Guiding Neural Machine Translation with Retrieved Translation Pieces](https://mlsanity.com/paper/1804.02559/) (2018)
- [Towards Automating Code Review Activities](https://mlsanity.com/paper/2101.02518/) (2021)
- [LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2308.11148/) (2023)
- [Retrieve and Refine: Exemplar-based Neural Comment Generation](https://mlsanity.com/paper/1910.10419/) (2019)
- [Incorporating Discrete Translation Lexicons into Neural Machine Translation](https://mlsanity.com/paper/1606.02006/) (2016)
- [AUGER: Automatically Generating Review Comments with Pre-training Models](https://mlsanity.com/paper/2208.08014/) (2022)
- [EditSum: A Retrieve-and-Edit Framework for Source Code Summarization](https://mlsanity.com/paper/2308.13775/) (2023)
- [Generation-based Code Review Automation: How Far Are We?](https://mlsanity.com/paper/2303.07221/) (2023)
- [Retrieval-Augmented Test Generation: How Far Are We?](https://mlsanity.com/paper/2409.12682/) (2024)
- [Improving Retrieval-Augmented Code Comment Generation by Retrieving for Generation](https://mlsanity.com/paper/2408.03623/) (2024)
- [Understanding Code Smell Detection via Code Review: A Study of the OpenStack Community](https://mlsanity.com/paper/2103.11446/) (2021)

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

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [RovoDev Code Reviewer: A Large-Scale Online Evaluation of LLM-based Code Review Automation at Atlassian](https://mlsanity.com/paper/2601.01129/) (2026)
- [When More Retrieval Hurts: Retrieval-Augmented Code Review Generation](https://mlsanity.com/paper/2511.05302/) (2025)
- [Q-Bridge: Code Translation for Quantum Machine Learning via LLMs](https://mlsanity.com/paper/2603.27836/) (2026)
- [OpenCodeReview: Determinism over Non-Determinism for Cost-Effective Agent-Based Code Review](https://mlsanity.com/paper/2608.09290/) (2026)
- [From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench](https://mlsanity.com/paper/2608.27442/) (2026)

## Abstract (arXiv)

Automated code review comment generation (RCG) aims to assist developers by automatically producing natural language feedback for code changes. Existing approaches are primarily either generation-based, using pretrained language models, or information retrieval-based (IR), reusing comments from similar past examples. While generation-based methods leverage code-specific pretraining on large code-natural language corpora to learn semantic relationships between code and natural language, they often struggle to generate low-frequency but semantically important tokens due to their probabilistic nature. In contrast, IR-based methods excel at recovering such rare tokens by copying from existing examples but lack flexibility in adapting to new code contexts-for example, when input code contains identifiers or structures not found in the retrieval database. To bridge the gap between generation-based and IR-based methods, this work proposes to leverage retrieval-augmented generation (RAG) for RCG by conditioning pretrained language models on retrieved code-review exemplars. By providing relevant examples that illustrate how similar code has been previously reviewed, the model is better guided to generate accurate review comments. Our evaluation on the Tufano et al. benchmark shows that RAG-based RCG outperforms both generation-based and IR-based RCG. It achieves up to +1.67% higher exact match and +4.25% higher BLEU scores compared to generation-based RCG. It also improves the generation of low-frequency ground-truth tokens by up to 24.01%. We additionally find that performance improves as the number of retrieved exemplars increases.