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.

翻译：在大数据时代，获取丰富数据对推动研究至关重要。然而，此类数据常因隐私问题或高昂成本而难以获取，尤其在医疗健康领域。生成合成（表格）数据可应对此挑战，但现有模型通常需要大量数据进行有效训练，这与我们解决数据稀缺问题的目标相悖。为应对这一挑战，我们提出一种新颖的合成表格数据生成框架，该框架由模拟生成对抗网络（GAN）架构的大语言模型（LLM）驱动。通过将数据生成过程作为上下文信息融入，并利用LLM作为优化器，我们的方法在常见的小样本场景中显著提升了合成数据生成的质量。我们在公开和私有数据集上的实验结果表明，在保持真实数据隐私的同时，本模型在生成更高质量合成数据以支持下游任务方面优于多种现有先进模型。