This article analyzes the use of Large Language Models (LLMs) as support 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. The experimental evaluation involved three LLMs, each subjected to three prompting techniques (Zero-Shot, Chain of Thought, and Chain of Thought + Verifier), applied to the same requirements scenario with progressively increasing complexity. The generated diagrams were qualitatively analyzed through direct comparison with the textual requirements, considering the structural and semantic adherence of the modeled elements. The results indicate that, although LLMs show reasonable performance in less complex scenarios, their reliability decreases as the complexity of the requirements increases, with a rise in inconsistencies, ambiguities, and failures in representing constraints. These findings reinforce that, in their current state, LLMs are not sufficiently mature for reliable use in complex scenarios, and the cost of validation may offset the apparent productivity gains.
Free University of Bozen-Bolzano, Italy(博洛尼亚-博兹纳自由大学,意大利);Université Paris-Saclay, CNRS, LISN, France(巴黎-萨克雷大学,法国 CNRS LISN);Birkbeck, University of London, UK(伦敦大学伯克贝克学院,英国);University of Huddersfield, UK(赫德斯菲尔德大学,英国);Relational AI, Berkeley, CA, USA(关系AI,美国加州伯克利);Hasselt University, Hasselt, Belgium(哈塞尔特大学,比利时);University of Wrocław, Poland(沃林福大学,波兰)
The AI Incident Database as an Educational Tool to Raise Awareness of AI Harms: A Classroom Exploration of Efficacy, Limitations, & Future Improvements