MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Data

TL;DR

This paper introduces MALLM-GAN, a novel framework using large language models as GANs to generate high-quality synthetic tabular data, especially effective with small sample sizes and privacy constraints.

Contribution

The paper presents a new LLM-based GAN architecture for synthetic tabular data generation that outperforms existing models in small data scenarios.

Findings

Outperforms state-of-the-art models in synthetic data quality.

Effective in small sample size scenarios.

Preserves privacy of real data.

Abstract

In the era of big data, access to abundant data is crucial for driving research forward. However, such data is often inaccessible due to privacy concerns or high costs, particularly in healthcare domain. Generating synthetic (tabular) data can address this, but existing models typically require substantial amounts of data to train effectively, contradicting our objective to solve data scarcity. To address this challenge, we propose a novel framework to generate synthetic tabular data, powered by large language models (LLMs) that emulates the architecture of a Generative Adversarial Network (GAN). By incorporating data generation process as contextual information and utilizing LLM as the optimizer, our approach significantly enhance the quality of synthetic data generation in common scenarios with small sample sizes. Our experimental results on public and private datasets demonstrate that our model outperforms several state-of-art models regarding generating higher quality synthetic data for downstream tasks while keeping privacy of the real data.