Optimization is Better than Generation: Optimizing Commit Message Leveraging Human-written Commit Message

2025/01/16 by Jiawei Li, David Faragó, Li, Jiawei +5 · 1 citation
Computer Science · #Context-Aware Activity Recognition Systems #FOS: Computer and information sciences #Software Engineering (cs.SE)

paper · pdf · doi:10.48550/arxiv.2501.09861

openalex publication_date 2025/01/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Commit messages are crucial in software development, supporting maintenance tasks and communication among developers. While Large Language Models (LLMs) have advanced Commit Message Generation (CMG) using various software contexts, some contexts developers consider are often missed by CMG techniques and can't be easily retrieved or even retrieved at all by automated tools. To address this, we propose Commit Message Optimization (CMO), which enhances human-written messages by leveraging LLMs and search-based optimization. CMO starts with human-written messages and iteratively improves them by integrating key contexts and feedback from external evaluators. Our extensive evaluation shows CMO generates commit messages that are significantly more Rational, Comprehensive, and Expressive while outperforming state-of-the-art CMG methods and human messages 88.2%-95.4% of the time.

Cited by

• CodeFuse-CommitEval: Towards Benchmarking LLM's Power on Commit Message and Code Change Inconsistency Detection

Related

• Consider What Humans Consider: Optimizing Commit Message Leveraging Contexts Considered By Human
• Context Conquers Parameters: Outperforming Proprietary LLM in Commit Message Generation
• From Commit Message Generation to History-Aware Commit Message Completion
• RAG-Enhanced Commit Message Generation
• Automated Commit Message Generation with Large Language Models: An Empirical Study and Beyond