Exploring Large Language Models’ Ability to Describe Entity-Relationship Schema-Based Conceptual Data Models
Open Access
- 29 April 2025
- journal article
- research article
- Published by MDPI AG in Information
- Vol. 16 (5) , 368
Abstract
In the field of databases, Large Language Models (LLMs) have recently been studied for generating SQL queries from textual descriptions, while their use for conceptual or logical data modeling remains less explored. The conceptual design of relational databases commonly relies on the entity-relationship (ER) data model, where translation rules enable mapping an ER schema into corresponding relational tables with their constraints. Our study investigates the capability of LLMs to describe in natural language a database conceptual data model based on the ER schema. Whether for documentation, onboarding, or communication with non-technical stakeholders, LLMs can significantly improve the process of explaining the ER schema by generating accurate descriptions about how the components interact as well as the represented information. To guide the LLM with challenging constructs, specific hints are defined to provide an enriched ER schema. Different LLMs have been explored (ChatGPT 3.5 and 4, Llama2, Gemini, Mistral 7B) and different metrics (F1 score, ROUGE, perplexity) are used to assess the quality of the generated descriptions and compare the different LLMs.Keywords
This publication has 26 references indexed in Scilit:
- Towards an understanding of large language models in software engineering tasksEmpirical Software Engineering, 2024
- Teaching UML using a RAG-based LLM2024
- Model Generation with LLMs: From Requirements to UML Sequence Diagrams2024
- A Large Language Model approach to SQL-to-Text Generation2024
- Generation of Textual/Video Descriptions for Technological Products Based on Structured Data2023
- Application of Large Language Models to Software Engineering Tasks: Opportunities, Risks, and ImplicationsIEEE Software, 2023
- A survey on deep learning approaches for text-to-SQLThe VLDB Journal, 2023
- Semantic coherence markers: The contribution of perplexity metricsArtificial Intelligence in Medicine, 2022
- Patent claim generation by fine-tuning OpenAI GPT-2World Patent Information, 2020
- M-SQL: Multi-Task Representation Learning for Single-Table Text2sql GenerationIEEE Access, 2020