Systematic Evaluation of Rule-Based Analytics for LLM-Driven Graph Data Modelling

Fabio Antonio Yanez, Andrés Montoyo, Armando Suárez, Alejandro Piad-Morffis, Yudivián Almeida Cruz


Abstract
This paper presents a novel multi-agent system for automatically generating graph database schemas from tabular data, strategically integrating rule-based analytics with large language models (LLMs). The framework leverages a lightweight rule system to select the most suitable analytic methods based on column data types, providing targeted insights that guide schema generation.
Anthology ID:
2025.r2lm-1.16
Volume:
Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Alicia Picazo-Izquierdo, Ernesto Luis Estevanell-Valladares, Ruslan Mitkov, Rafael Muñoz Guillena, Raúl García Cerdá
Venues:
R2LM | WS
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
154–164
Language:
URL:
https://aclanthology.org/2025.r2lm-1.16/
DOI:
Bibkey:
Cite (ACL):
Fabio Antonio Yanez, Andrés Montoyo, Armando Suárez, Alejandro Piad-Morffis, and Yudivián Almeida Cruz. 2025. Systematic Evaluation of Rule-Based Analytics for LLM-Driven Graph Data Modelling. In Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models, pages 154–164, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
Systematic Evaluation of Rule-Based Analytics for LLM-Driven Graph Data Modelling (Yanez et al., R2LM 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.r2lm-1.16.pdf