mlsanityData to 7 Oct 2026

RACE: Retrieval-Augmented Commit Message Generation

arXiv 2203.02700 ↗First posted 5 Mar 2022cs.SE cs.AI cs.LGcited by 27

On the map: Retrieval-augmented generation → RAG for code

Abstract (arXiv)

Commit messages are important for software development and maintenance. Many neural network-based approaches have been proposed and shown promising results on automatic commit message generation. However, the generated commit messages could be repetitive or redundant. In this paper, we propose RACE, a new retrieval-augmented neural commit message generation method, which treats the retrieved similar commit as an exemplar and leverages it to generate an accurate commit message. As the retrieved commit message may not always accurately describe the content/intent of the current code diff, we also propose an exemplar guider, which learns the semantic similarity between the retrieved and current code diff and then guides the generation of commit message based on the similarity. We conduct extensive experiments on a large public dataset with five programming languages. Experimental results show that RACE can outperform all baselines. Furthermore, RACE can boost the performance of existing Seq2Seq models in commit message generation.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Placed in RAG for code, one of 15 directions in Retrieval-augmented generation. Builds on 17 of its 44 references that are in the map. First posted on arXiv 5 Mar 2022.

Builds on

17 of 44 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  4. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  5. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  6. 2021On the Evaluation of Neural Code Summarizationcited by 47
  7. 2021Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedbackcited by 45
  8. 2017Automatically Generating Commit Messages from Diffs using Neural Machine Translationcited by 42
  9. 2019Retrieve and Refine: Exemplar-based Neural Comment Generationcited by 36
  10. 2021CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Treescited by 31
  11. 2020Learning to Update Natural Language Comments Based on Code Changescited by 30
  12. 2019ATOM: Commit Message Generation Based on Abstract Syntax Tree and Hybrid Rankingcited by 25
5 more
  1. 2017A Neural Architecture for Generating Natural Language Descriptions from Source Code Changescited by 23
  2. 2021On the Evaluation of Commit Message Generation Models: An Experimental Studycited by 20
  3. 2021CommitBERT: Commit Message Generation Using Pre-Trained Programming Language Modelcited by 16
  4. 2020CoreGen: Contextualized Code Representation Learning for Commit Message Generationcited by 15
  5. 2015Untangling Fine-Grained Code Changescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 9; 2025: 7; 2026: 7.

27 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  2. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  3. 2024Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAGcited by 67
  4. 2024Agents in Software Engineering: Survey, Landscape, and Visioncited by 60
  5. 2025Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generationcited by 42
  6. 2024RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processingcited by 25
  7. 2022CoCoSoDa: Effective Contrastive Learning for Code Searchcited by 21
  8. 2023From Commit Message Generation to History-Aware Commit Message Completioncited by 16
  9. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  10. 2024KADEL: Knowledge-Aware Denoising Learning for Commit Message Generationcited by 10
  11. 2023SoTaNa: The Open-Source Software Development Assistantcited by 8
  12. 2025RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detectioncited by 8
15 more
  1. 2026AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completioncited by 7
  2. 2024A Methodology for Evaluating RAG Systems: A Case Study On Configuration Dependency Validationcited by 6
  3. 2024ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusioncited by 5
  4. 2025Impact-driven Context Filtering For Cross-file Code Completioncited by 5
  5. 2025SecureReviewer: Enhancing Large Language Models for Secure Code Review through Secure-aware Fine-tuningcited by 5
  6. 2024COMET: Generating Commit Messages using Delta Graph Context Representationcited by 3
  7. 2026DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoningcited by 3
  8. 2026Code Change Characteristics and Description Alignment: A Comparative Study of Agentic versus Human Pull Requestscited by 2
  9. 2026PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agentscited by 2
  10. 2025CodeFuse-CommitEval: Towards Benchmarking LLM's Power on Commit Message and Code Change Inconsistency Detectioncited by 1
  11. 2025Political Events using RAG with LLMscited by 0
  12. 2025CoRaCMG: Contextual Retrieval-Augmented Framework for Commit Message Generationcited by 0
  13. 2026RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generationcited by 0
  14. 2026Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generationcited by 0
  15. 2026Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024RAG-Enhanced Commit Message Generation
  2. 2026CoRaCommit: A VS Code Extension for Commit Message Generation with Exemplar Retrieval ↗
  3. 2026Conventional Commit Classification using Large Language Models and Prompt Engineering
  4. 2025Evaluating Generated Commit Messages with Large Language Models
  5. 2025Repository-level Code Search with Neural Retrieval Methods
  6. 2025Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches
  7. 2025FastCoder: Accelerating Repository-level Code Generation via Efficient Retrieval and Verification
  8. 2024Improving Retrieval-Augmented Code Comment Generation by Retrieving for Generation