# What Makes a Good Commit Message?

arXiv: https://arxiv.org/abs/2202.02974 · HTML: https://mlsanity.com/paper/2202.02974/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2022.

## Built on by (most cited first, 20 of 20)

- [From Commit Message Generation to History-Aware Commit Message Completion](https://mlsanity.com/paper/2308.07655/) (2023)
- [KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation](https://mlsanity.com/paper/2401.08376/) (2024)
- [Towards an Understanding of Context Utilization in Code Intelligence](https://mlsanity.com/paper/2504.08734/) (2025)
- [CommitBench: A Benchmark for Commit Message Generation](https://mlsanity.com/paper/2403.05188/) (2024)
- [LAURA: Enhancing Code Review Generation with Context-Enriched Retrieval-Augmented LLM](https://mlsanity.com/paper/2512.01356/) (2025)
- [Can GPT-4 Replicate Empirical Software Engineering Research?](https://mlsanity.com/paper/2310.01727/) (2023)
- [Hallucinations in Code Change to Natural Language Generation: Prevalence and Evaluation of Detection Metrics](https://mlsanity.com/paper/2508.08661/) (2025)
- [COMET: Generating Commit Messages using Delta Graph Context Representation](https://mlsanity.com/paper/2402.01841/) (2024)
- [Code Change Characteristics and Description Alignment: A Comparative Study of Agentic versus Human Pull Requests](https://mlsanity.com/paper/2601.17627/) (2026)
- [Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding](https://mlsanity.com/paper/2608.11095/) (2026)
- [A Full-fledged Commit Message Quality Checker Based on Machine Learning](https://mlsanity.com/paper/2309.04797/) (2023)
- [Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs](https://mlsanity.com/paper/2604.20211/) (2026)
- [Mitigating Sensitive Information Leakage in LLMs4Code through Machine Unlearning](https://mlsanity.com/paper/2502.05739/) (2025)
- [CodeFuse-CommitEval: Towards Benchmarking LLM's Power on Commit Message and Code Change Inconsistency Detection](https://mlsanity.com/paper/2511.19875/) (2025)
- [Pull Requests as a Training Signal for Repo-Level Code Editing](https://mlsanity.com/paper/2602.07457/) (2026)
- [An Empirical Study of Downstream Adaptation for Agent Skills](https://mlsanity.com/paper/2607.03238/) (2026)
- [Towards Realistic Evaluation of Commit Message Generation by Matching Online and Offline Settings](https://mlsanity.com/paper/2410.12046/) (2024)
- [AI-Powered Commit Explorer (APCE)](https://mlsanity.com/paper/2507.16063/) (2025)
- [CoRaCMG: Contextual Retrieval-Augmented Framework for Commit Message Generation](https://mlsanity.com/paper/2509.18337/) (2025)
- [Towards Automatically Pruning Logging Code with Coding Agents: How Far Are We?](https://mlsanity.com/paper/2610.04716/) (2026)

## Abstract (arXiv)

A key issue in collaborative software development is communication among developers. One modality of communication is a commit message, in which developers describe the changes they make in a repository. As such, commit messages serve as an "audit trail" by which developers can understand how the source code of a project has changed-and why. Hence, the quality of commit messages affects the effectiveness of communication among developers. Commit messages are often of poor quality as developers lack time and motivation to craft a good message. Several automatic approaches have been proposed to generate commit messages. However, these are based on uncurated datasets including considerable proportions of poorly phrased commit messages. In this multi-method study, we first define what constitutes a "good" commit message, and then establish what proportion of commit messages lack information using a sample of almost 1,600 messages from five highly active open source projects. We find that an average of circa 44% of messages could be improved, suggesting the use of uncurated datasets may be a major threat when commit message generators are trained with such data. We also observe that prior work has not considered semantics of commit messages, and there is surprisingly little guidance available for writing good commit messages. To that end, we develop a taxonomy based on recurring patterns in commit messages' expressions. Finally, we investigate whether "good" commit messages can be automatically identified; such automation could prompt developers to write better commit messages.