From natural language to knowledge: The Role of LLMs in conceptual and data modeling

The convergence of natural language processing and data-centric system design has long been a defining theme of the International Conference on Natural Language & Information Systems, especially, the transformation of natural language into structured knowledge through conceptual modeling, database design, and intelligent information systems. Recent advances in Large Language Models (LLMs) and Generative AI have significantly expanded this research landscape, enabling new approaches to requirement interpretation, schema induction, natural-language querying, and multimodal knowledge representation. This paper explores the evolving role of LLMs in conceptual and data modeling, highlighting how generative models augment and challenge established modeling principles. We present some of the important topics in current research at the intersection of conceptual modeling and LLMs. We also introduce the best papers from the 29th International Conference on Natural Language & Information Systems (NLDB 2024) held in Turin, Italy, and summarize their valuable contributions. We conclude with suggestions for continued research with primary focus on how classical modeling foundations and modern generative AI techniques can be combined to support rigorous, interpretable, and human-centered data and knowledge engineering in increasingly complex and multilingual environments.