PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 5, 2026ACM Transactions on Software Engineering and Methodology0 citations

Delving into History: Retrieve Less but Augment More on Commit Message Generation

View Full Paper
PLPeng LanJLJiakun LiuXZXinyu Zhong

Key Points

  • The aim is to enhance commit message generation by leveraging relevant context from commit history.
  • Proposed a new approach called HisRag to retrieve relevant commit messages from history.
  • Conducted extensive experiments to evaluate HisRag's performance against various existing methods.
  • Measured performance using metrics like B-NORM, BLEU, ROUGE-L, and others.
  • HisRag achieved average improvements of 65% in B-NORM and 78% in BLEU metrics.
  • Significant increases were found in ROUGE-L (38%) and METEOR (42%) scores.
  • Human evaluation indicated better informativeness, conciseness, and expressiveness of generated messages.

Abstract

Commit messages are crucial to software development and maintenance, allowing developers to track code changes and collaborate effectively. Automating commit message generation (CMG) reduces developers’ manual effort and facilitates program comprehension and software maintenance. Previous approaches typically generate commit messages based solely on code changes, overlooking the valuable context provided by commit history. Moreover, different developers have varying background knowledge and work on different tasks, leading to diverse commit message styles. The commit history provides important context when developers handle different software development tasks across different repositories, yet its potential in CMG remains underexplored. To fill this gap, we propose a novel paradigm named HisRag , which retrieves relevant commit messages from commit history and uses them to enhance existing CMG approaches, improving the quality and relevance of generated commit messages. Extensive experiments showed that HisRag significantly enhances the performance of various CMG approaches. The average improvements on the B-NORM, BLEU, ROUGE-L, METEOR, Log-MNEXT, and BRSA are 65%, 78%, 38%, 42%, 37%, and 12%, and the human evaluation results indicate that HisRag can improve CMG approaches in terms of informativeness, conciseness, expressiveness, and acceptance rate, providing meaningful insights for future research on history retrieval-augmented commit message generation and practical application.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Lan et al. (2026) studied this question.

synapsesocial.com/papers/6984358ff1d9ada3c1fb480fhttps://doi.org/10.1145/3794857
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1RAG-Enhanced Commit Message Generation2024 · 2 citations
  2. 2Contextual Code Retrieval for Commit Message Generation: A Preliminary Study2025
  3. 3Is It Hard to Generate Holistic Commit Message?2024 · 4 citations
  4. 4Automated Commit Message Generation with Large Language Models: An Empirical Study and Beyond2024 · 1 citations
  5. 5AI-Driven Code Documentation: Comparative Evaluation of LLMs for Commit Message Generation2026