# When More Retrieval Hurts: Retrieval-Augmented Code Review Generation

arXiv: https://arxiv.org/abs/2511.05302 · HTML: https://mlsanity.com/paper/2511.05302/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 7 Nov 2025.

## Placed in

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

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Retrieval Augmented Code Generation and Summarization](https://mlsanity.com/paper/2108.11601/) (2021)
- [Unified Demonstration Retriever for In-Context Learning](https://mlsanity.com/paper/2305.04320/) (2023)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory](https://mlsanity.com/paper/2305.02437/) (2023)
- [Automating Code Review Activities by Large-Scale Pre-training](https://mlsanity.com/paper/2203.09095/) (2022)
- [Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning](https://mlsanity.com/paper/2304.11384/) (2023)
- [Using Pre-Trained Models to Boost Code Review Automation](https://mlsanity.com/paper/2201.06850/) (2022)
- [Augmenting Transformers with KNN-Based Composite Memory for Dialogue](https://mlsanity.com/paper/2004.12744/) (2020)
- [LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2308.11148/) (2023)
- [Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering](https://mlsanity.com/paper/2004.11892/) (2020)
- [AUGER: Automatically Generating Review Comments with Pre-training Models](https://mlsanity.com/paper/2208.08014/) (2022)
- [PISCO: Pretty Simple Compression for Retrieval-Augmented Generation](https://mlsanity.com/paper/2501.16075/) (2025)
- [EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.12559/) (2024)
- [CORE: Automating Review Recommendation for Code Changes](https://mlsanity.com/paper/1912.09652/) (2019)
- [Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking](https://mlsanity.com/paper/2307.01453/) (2023)
- [SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression](https://mlsanity.com/paper/2507.05633/) (2025)
- [RAG-Enhanced Commit Message Generation](https://mlsanity.com/paper/2406.05514/) (2024)
- [Retrieval-Augmented Code Review Comment Generation](https://mlsanity.com/paper/2506.11591/) (2025)
- [Suggestion Bot: Analyzing the Impact of Automated Suggested Changes on Code Reviews](https://mlsanity.com/paper/2305.06328/) (2023)
- [Retrieval-Augmented Semantic Parsing: Improving Generalization with Lexical Knowledge](https://mlsanity.com/paper/2412.10207/) (2024)

## Built on by (most cited first, 2 of 2)

- [The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context](https://mlsanity.com/paper/2608.14838/) (2026)
- [From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench](https://mlsanity.com/paper/2608.27442/) (2026)

## Abstract (arXiv)

Code review generation can reduce developer effort by producing concise, reviewer-style feedback for a given code snippet or code change. However, generation-only models often produce generic or off-point reviews, while retrieval-only methods struggle to adapt well to new contexts. In this paper, we view retrieval augmentation for code review as retrieval-augmented in-context learning, where retrieved historical reviews are placed in the input context as examples that guide the model's output. Based on this view, we propose RARe (Retrieval-Augmented Code Reviewer), a framework that retrieves relevant historical reviews from a corpus and conditions a large language model on the retrieved in-context examples. Experiments on two public benchmarks show that RARe outperforms strong baselines and reaches BLEU-4 scores of 12.32 and 12.96. A key finding is that more retrieval can hurt: using only the top-1 retrieved example works best, while adding more retrieved items can degrade performance due to redundancy and conflicting cues under limited context budgets. Human evaluation and interpretability analysis further support that retrieval-augmented generation reduces generic outputs and improves review focus.