TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generation
This addresses the computational expense of fine-tuning for tabular data generation, offering a more efficient method for researchers and practitioners in data science.
The paper tackles the problem of generating synthetic tabular data using large language models (LLMs) without fine-tuning, by proposing TabGen-ICL, a framework that selects in-context examples based on residuals to improve generation quality. It reduces error rates by 3.5% to 42.2% on fidelity metrics across five datasets.
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}.