返回
AI-Driven Code Documentation: Comparative Evaluation of LLMs for Commit Message Generation
DOI:10.3390/computers15020087.png)
摘要
En
Keyword:
large language models
commit message generation
retrieval-augmented generation
CommitBench
transformer-based models
automatic and human evaluation
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
C
IF:
4.2
论文数:
1.4K
被引数:
3.3K
机构
引用论文
CoreGen: Contextualized Code Representation Learning for Commit Message Generation
NEUROCOMPUTING
IF6.5
MFGAN: Multimodal Fusion for Industrial Anomaly Detection Using Attention-Based Autoencoder and Generative Adversarial NetworkMFGAN: 使用基于注意力的自动编码器和生成对抗网络进行工业异常检测的多模态融合
SENSORS
IF3.5
Automatic Commit Message Generation: A Critical Review and Directions for Future Work自动提交消息生成: 关键回顾和未来工作方向
Joshi, S. A review of generative AI and DevOps pipelines: CI/CD, agentic automation, MLOps integration, and large language models. Int. J. Innov. Res. Comput. Sci. Technol. 2025, 13, 1–14. [Google Scholar] [CrossRef]Joshi, S. 生成式AI和DevOps流水线的综述:CI/CD、代理自动化、MLOps集成及大型语言模型. 国际计算机科学与技术创新杂志. 2025, 13, 1–14. [Google Scholar] [CrossRef]

