From Conceptual to Logical Schema: An LLM-based Approach

• Hudson Afonso Batista da Silva UFSC
• Vitória Soares dos Santos UFSC
• Carina Friedrich Dorneles UFSC
• Ronaldo dos Santos Mello UFSC

DOI: https://doi.org/10.5753/eramiars.2025.16661

Resumo

The use of language models for solving computational tasks has grown in recent years. Generating logical models from conceptual modeling (ER) is a specialized task with well-defined rules, performed by database specialists. This paper presents an experimental investigation into the capabilities of large language models (LLMs), including GPT, Gemini, and Claude, in generating logical models from conceptual representations. The results demonstrate that the Claude model exhibits superior results in addressing the proposed task.

Referências

Avignone, A., Tierno, A., Fiori, A., and Chiusano, S. (2025). Exploring large language models’ ability to describe entity-relationship schema-based conceptual data models. Information, 16(5):368.

Elmasri, R. and Navathe, S. B. (2016). Fundamentals of database systems seventh edition.

Härer, F. (2023). Conceptual model interpreter for large language models. arXiv preprint arXiv:2311.07605.

Li, G., Zhou, X., and Zhao, X. (2024). Llm for data management. Proceedings of the VLDB Endowment, 17(12):4213–4216.

Liu, X., Shen, S., Li, B., Ma, P., Jiang, R., Zhang, Y., Fan, J., Li, G., Tang, N., and Luo, Y. (2025). A survey of text-to-sql in the era of llms: Where are we, and where are we going? IEEE Transactions on Knowledge and Data Engineering.

Mylopoulos, J., Guizzardi, G., and Guarino, N. (2025). Conceptual modeling: Foundations, a historical perspective, and a vision for the future. Data & Knowledge Engineering, 160:102483.

Salem, N., Al-Tarawneh, K., Hudaib, A., Salem, H., Tareef, A., Salloum, H., and Mazzara, M. (2025). Generating database schema from requirement specification based on natural language processing and large language model. COMPUTER, 16(7):1703–1713.

Singh, A., Shetty, A., Ehtesham, A., Kumar, S., and Khoei, T. T. (2025). A survey of large language model-based generative ai for text-to-sql: Benchmarks, applications, use cases, and challenges. In 2025 IEEE 15th Annual Computing and Communication Workshop and Conference (CCWC), pages 00015–00021. IEEE.

Visperas, M., Adoptante, A. J., Borjal, C. J., Abia, M. T., Catapang, J. K., and Peramo, E. (2023). On modern text-to-sql semantic parsing methodologies for natural language interface to databases: A comparative study. In 2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pages 390–396. IEEE.

Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., and Zhang, Y. (2024). A survey on large language model (llm) security and privacy: The good, the bad, and the ugly. 4(2):100211.