Netz, LukasMichael, JudithRumpe, BernhardMichael, JudithWeske, Mathias2024-02-192024-02-192024978-3-88579-742-5https://dl.gi.de/handle/20.500.12116/43620We evaluate the usage of Large Language Models (LLMs) to transform natural language into models of a predefined domain-specific language within the context of model-driven software engineering. In this work we test systematically the reliability and correctness of the developed tooling, to ensure its usability in an automated model-driven engineering context. Up to now, LLMs such as ChatGPT were not sophisticated enough to yield promising results. The new API-Access and the release of GPT-4, enabled us to develop improved tooling that can be evaluated systematically. This paper introduces an approach that can produce a running web application based on simple informal specifications, that is provided by a domain expert with no prior knowledge of any DSL. We extended our toolchain to include ChatGPT and provided the AI with additional DSL-specific contexts in order to receive models that can be further processed. We performed tests to ensure the semantic and syntactic correctness of the created models. This approach shows the potential of LLMs to successfully bridge the gap between domain experts and developers and discusses its current limitations.enChatGPTGPT-4Model-Driven EngineeringCode GenerationMontiGemDSLText/Conference Paper10.18420/modellierung2024_0181617-5468