# CoRaCMG: Contextual Retrieval-Augmented Framework for Commit Message Generation

arXiv: https://arxiv.org/abs/2509.18337 · HTML: https://mlsanity.com/paper/2509.18337/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 13 of its 36 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Placed in

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

## Builds on (most cited first, 13 of 13)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://mlsanity.com/paper/2309.06057/) (2023)
- [Automatically Generating Commit Messages from Diffs using Neural Machine Translation](https://mlsanity.com/paper/1708.09492/) (2017)
- [CC2Vec: Distributed Representations of Code Changes](https://mlsanity.com/paper/2003.05620/) (2020)
- [RACE: Retrieval-Augmented Commit Message Generation](https://mlsanity.com/paper/2203.02700/) (2022)
- [ATOM: Commit Message Generation Based on Abstract Syntax Tree and Hybrid Ranking](https://mlsanity.com/paper/1912.02972/) (2019)
- [A Neural Architecture for Generating Natural Language Descriptions from Source Code Changes](https://mlsanity.com/paper/1704.04856/) (2017)
- [What Makes a Good Commit Message?](https://mlsanity.com/paper/2202.02974/) (2022)
- [CoreGen: Contextualized Code Representation Learning for Commit Message Generation](https://mlsanity.com/paper/2007.06934/) (2020)
- [Using Large Language Models for Commit Message Generation: A Preliminary Study](https://mlsanity.com/paper/2401.05926/) (2024)
- [Contextual Code Retrieval for Commit Message Generation: A Preliminary Study](https://mlsanity.com/paper/2507.17690/) (2025)

## Abstract (arXiv)

Commit messages play a key role in documenting the intent behind code changes. However, they are often low-quality, vague, or incomplete, limiting their usefulness. Commit Message Generation (CMG) aims to automatically generate descriptive commit messages from code diffs to reduce developers' effort and improve message quality. Although recent advances in LLMs have shown promise in automating CMG, their performance remains limited. This paper aims to enhance CMG performance by retrieving similar diff-message pairs to guide LLMs to generate commit messages that are more precise and informative. We proposed CoRaCMG, a Contextual Retrieval-augmented framework for Commit Message Generation, structured in three phases: (1) Retrieve: retrieving the similar diff-message pairs; (2) Augment: combining them with the query diff into a structured prompt; and (3) Generate: generating commit messages corresponding to the query diff via LLMs. CoRaCMG enables LLMs to learn project-specific terminologies and writing styles from the retrieved diff-message pairs. We evaluated CoRaCMG across multiple LLMs (e.g., GPT, DeepSeek, and Qwen) and compared its performance against SOTA baselines. Experimental results show that CoRaCMG significantly boosts LLM performance across four metrics (BLEU, Rouge-L, METEOR, and CIDEr). Specifically, DeepSeek-R1 achieves relative improvements of 76% in BLEU and 71% in CIDEr when augmented with a single retrieved example pair. After incorporating the single example pair, GPT-4o achieves the highest improvement rate, with BLEU increasing by 89%. Moreover, performance gains plateau after more than three examples are used, indicating diminishing returns. Further analysis shows that the improvements are attributed to the model's ability to capture the terminologies and writing styles of human-written commit messages from the retrieved example pairs.