MDENet Annual Symposium 2023 recordings and presentation slides

Thanks to the rapid evolution of Artificial Intelligence (AI) in recent years we constantly have new mechanisms at our disposal that allow us to solve increasingly complex problems. Lately, Large Language Models (LLMs) is the subfield of AI that is revolutionising many sectors, including Software Engineering and in particular MBSE.

By leveraging AI and LLMs in MBSE, we can provide modelers with intelligent assistants as well as automate tasks that help them develop higher-quality software to improve their productivity. This shift from mostly manual tasks to AI-assisted and AI-automated tasks enables modellers to spend their time on the tasks where they provide the most value.

In this talk I give an overview of our work that leverages LLMs to assist modelers when creating models, and evaluates the current capabilities of widespread LLMs, such as GPT-3.5 and GPT-4. Finally, I present both the short-term and long-term challenges that we will be facing in the future.