# COMET: Generating Commit Messages using Delta Graph Context Representation

arXiv: https://arxiv.org/abs/2402.01841 · HTML: https://mlsanity.com/paper/2402.01841/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 90 references that are in the map.
- First posted on arXiv 2 Feb 2024.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](https://mlsanity.com/paper/1909.03496/) (2019)
- [A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets](https://mlsanity.com/paper/2305.18486/) (2023)
- [Is ChatGPT the Ultimate Programming Assistant -- How far is it?](https://mlsanity.com/paper/2304.11938/) (2023)
- [Automatically Generating Commit Messages from Diffs using Neural Machine Translation](https://mlsanity.com/paper/1708.09492/) (2017)
- [Deep API Learning](https://mlsanity.com/paper/1605.08535/) (2016)
- [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)
- [On the Evaluation of Commit Message Generation Models: An Experimental Study](https://mlsanity.com/paper/2107.05373/) (2021)
- [What Makes a Good Commit Message?](https://mlsanity.com/paper/2202.02974/) (2022)
- [CommitBERT: Commit Message Generation Using Pre-Trained Programming Language Model](https://mlsanity.com/paper/2105.14242/) (2021)
- [CoreGen: Contextualized Code Representation Learning for Commit Message Generation](https://mlsanity.com/paper/2007.06934/) (2020)
- [Boosting Automatic Commit Classification Into Maintenance Activities By Utilizing Source Code Changes](https://mlsanity.com/paper/1711.05340/) (2017)
- [Generating Commit Messages from Git Diffs](https://mlsanity.com/paper/1911.11690/) (2019)
- [On the Impact of Multiple Source Code Representations on Software Engineering Tasks -- An Empirical Study](https://mlsanity.com/paper/2106.10918/) (2021)

## Built on by (most cited first, 3 of 3)

- [Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models](https://mlsanity.com/paper/2407.00456/) (2024)
- [Towards an Understanding of Context Utilization in Code Intelligence](https://mlsanity.com/paper/2504.08734/) (2025)
- [ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation](https://mlsanity.com/paper/2601.09703/) (2026)

## Abstract (arXiv)

Commit messages explain code changes in a commit and facilitate collaboration among developers. Several commit message generation approaches have been proposed; however, they exhibit limited success in capturing the context of code changes. We propose Comet (Context-Aware Commit Message Generation), a novel approach that captures context of code changes using a graph-based representation and leverages a transformer-based model to generate high-quality commit messages. Our proposed method utilizes delta graph that we developed to effectively represent code differences. We also introduce a customizable quality assurance module to identify optimal messages, mitigating subjectivity in commit messages. Experiments show that Comet outperforms state-of-the-art techniques in terms of bleu-norm and meteor metrics while being comparable in terms of rogue-l. Additionally, we compare the proposed approach with the popular gpt-3.5-turbo model, along with gpt-4-turbo; the most capable GPT model, over zero-shot, one-shot, and multi-shot settings. We found Comet outperforming the GPT models, on five and four metrics respectively and provide competitive results with the two other metrics. The study has implications for researchers, tool developers, and software developers. Software developers may utilize Comet to generate context-aware commit messages. Researchers and tool developers can apply the proposed delta graph technique in similar contexts, like code review summarization.