AI RESEARCH
On the Limitations of Large Language Models for Conceptual Database Modeling
arXiv CS.AI
•
ArXi:2605.11986v1 Announce Type: new This article analyzes the use of Large Language Models (LLMs) as for the conceptual modeling of relational databases through the automatic generation of Entity-Relationship (ER) diagrams from natural language requirements. The approach combines different language models with prompt engineering techniques to evaluate their ability to identify entities, relationships, and attributes in a conceptually consistent manner.