用大模型辅助建模，减少对领域数据依赖，提升设计效率。
On the Utility of Domain Modeling Assistance with Large Language Models
- 基于少样本提示学习的LLM辅助建模，无需大量领域数据训练。
- 工具MAGDA支持多种建模任务，用户研究验证其有效性。
- 适合软件建模者快速生成符合规范的领域模型，尤其在数据不足时。
模型驱动工程（MDE）通过抽象简化软件开发，但时间压力、领域理解不全及语法约束等问题仍制约设计过程。本文提出一种利用大语言模型（LLMs）与少样本提示学习的新方法，旨在克服基于AI的补全模型在稀缺领域数据上训练的难题，并为各类建模活动提供灵活支持，向软件建模者提供有价值的建议。为此，我们开发了易用工具MAGDA，通过用户研究评估该方法在真实场景中对领域建模的适用性，揭示其可用性与有效性，为实际应用提供重要洞见。
原文摘要 · Abstract (English)
Model-driven engineering (MDE) simplifies software development through abstraction, yet challenges such as time constraints, incomplete domain understanding, and adherence to syntactic constraints hinder the design process. This paper presents a study to evaluate the usefulness of a novel approach utilizing large language models (LLMs) and few-shot prompt learning to assist in domain modeling. The aim of this approach is to overcome the need for extensive training of AI-based completion models on scarce domain-specific datasets and to offer versatile support for various modeling activities, providing valuable recommendations to software modelers. To support this approach, we developed MAGDA, a user-friendly tool, through which we conduct a user study and assess the real-world applicability of our approach in the context of domain modeling, offering valuable insights into its usability and effectiveness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。