Large language models (LLMs) have demonstrated remarkable in-context learning capabilities across diverse applications. In this work, we explore the effectiveness of LLMs for generating realistic synthetic tabular data, identifying key prompt design elements to optimize performance. We introduce EPIC, a novel approach that leverages balanced, grouped data samples and consistent formatting with unique variable mapping to guide LLMs in generating accurate synthetic data across all classes, even for imbalanced datasets. Evaluations on real-world datasets show that EPIC achieves state-of-the-art machine learning classification performance, significantly improving generation efficiency. These findings highlight the effectiveness of EPIC for synthetic tabular data generation, particularly in addressing class imbalance. Our source code for our work is available at: https://seharanul17.github.io/project-synthetic-tabular-llm/

翻译：大语言模型（LLM）已在多种应用中展现出卓越的上下文学习能力。本研究探讨了利用LLM生成真实合成表格数据的有效性，并确定了优化性能的关键提示设计要素。我们提出了EPIC这一新方法，该方法利用平衡的分组数据样本、保持一致的格式以及独特的变量映射，引导LLM为所有类别（即使是不平衡数据集）生成准确的合成数据。在真实数据集上的评估表明，EPIC实现了最先进的机器学习分类性能，并显著提升了生成效率。这些发现突显了EPIC在合成表格数据生成方面的有效性，尤其是在处理类别不平衡问题上。本工作的源代码公开于：https://seharanul17.github.io/project-synthetic-tabular-llm/