发表机构
European Chips Joint Undertaking; Federal Ministry of Research, Technology and Space of Germany（欧洲芯片联合体; 德国联邦研究、科技与航天部）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究汽车领域异构建模工具互操作性难题，提出基于大语言模型驱动的方法，涉及模型实例到目标元模型的映射及元模型合并，经案例验证该方法可行，能减少手动转换工作量并生成有效目标模型促进跨工具互操作。
AI 中文摘要
在模型驱动工程（MDE）中，异构建模工具之间的互操作性仍然是一个重大挑战，尤其是在汽车领域，多种建模语言以及事实上的标准专有和开源工具并存。本文提出一种基于大语言模型（LLM）驱动的方法来实现自动模型互操作性，考虑两个相关方面：一是将模型实例映射到目标元模型，二是元模型合并。通过涉及基于Ecore和SysML v2的元模型的转换来演示所提出的方法，并针对用户定义的目标模型对生成的模型实例进行结构验证。汽车领域的案例研究说明了该方法的可行性，表明大语言模型可以显著减少手动转换工作量，同时生成用于跨工具互操作性的结构有效的目标模型。
英文摘要
Interoperability between heterogeneous modeling tools remains a significant challenge in Model-Driven Engineering (MDE), particularly in the automotive domain where multiple modeling languages, as well as defacto standard proprietary and open-source tools coexist. This paper presents an LLM-driven approach for automated model interoperability by considering two relevant aspects: 1) mapping model instances to a target metamodel 2) merging of metamodels. The proposed methodology is demonstrated through transformations involving Ecore and SysML v2 based metamodels and incorporates structural validation of generated model instances against user-defined target models. Automotive case studies illustrate the feasibility of the approach and show that large language models can significantly reduce manual transformation effort while generating structurally valid target models for cross-tool interoperability.
