Assessing Generative Models for Structured Data (2503.20903v1)

Abstract: Synthetic tabular data generation has emerged as a promising method to address limited data availability and privacy concerns. With the sharp increase in the performance of LLMs in recent years, researchers have been interested in applying these models to the generation of tabular data. However, little is known about the quality of the generated tabular data from LLMs. The predominant method for assessing the quality of synthetic tabular data is the train-synthetic-test-real approach, where the artificial examples are compared to the original by how well machine learning models, trained separately on the real and synthetic sets, perform in some downstream tasks. This method does not directly measure how closely the distribution of generated data approximates that of the original. This paper introduces rigorous methods for directly assessing synthetic tabular data against real data by looking at inter-column dependencies within the data. We find that LLMs (GPT-2), both when queried via few-shot prompting and when fine-tuned, and GAN (CTGAN) models do not produce data with dependencies that mirror the original real data. Results from this study can inform future practice in synthetic data generation to improve data quality.