TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generation

TL;DR

This paper introduces TabGen-ICL, a novel iterative in-context learning framework that improves tabular data generation by selecting residual-aware examples, significantly outperforming random selection strategies.

Contribution

It proposes a residual-aware, iterative example selection method for fixed LLM prompting, enhancing tabular data generation without fine-tuning.

Findings

Outperforms random selection in experiments

Reduces error rate by 3.5%-42.2% on fidelity metrics

First to demonstrate high-quality synthetic tabular data from fixed LLMs

Abstract

Large Language models (LLMs) have achieved encouraging results in tabular data generation. However, existing approaches require fine-tuning, which is computationally expensive. This paper explores an alternative: prompting a fixed LLM with in-context examples. We observe that using randomly selected in-context examples hampers the LLM's performance, resulting in sub-optimal generation quality. To address this, we propose a novel in-context learning framework: TabGen-ICL, to enhance the in-context learning ability of LLMs for tabular data generation. TabGen-ICL operates iteratively, retrieving a subset of real samples that represent the residual between currently generated samples and true data distributions. This approach serves two purposes: locally, it provides more effective in-context learning examples for the LLM in each iteration; globally, it progressively narrows the gap between generated and real data. Extensive experiments on five real-world tabular datasets demonstrate that TabGen-ICL significantly outperforms the random selection strategy. Specifically, it reduces the error rate by a margin of $3.5\%-42.2\%$ on fidelity metrics. We demonstrate for the first time that prompting a fixed LLM can yield high-quality synthetic tabular data. The code is provided in the \href{https://github.com/fangliancheng/TabGEN-ICL}{link}.