@inproceedings{fang-etal-2025-tabgen,
    title = "{TABGEN}-{ICL}: Residual-Aware In-Context Example Selection for Tabular Data Generation",
    author = "Fang, Liancheng  and
      Liu, Aiwei  and
      Zhang, Hengrui  and
      Zou, Henry Peng  and
      Zhang, Weizhi  and
      Yu, Philip S.",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.findings-acl.1027/",
    doi = "10.18653/v1/2025.findings-acl.1027",
    pages = "20027--20041",
    ISBN = "979-8-89176-256-5",
    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 up to 42.2{\%} on the fidelity metric. We demonstrate for the first time that prompting a fixed LLM can yield high-quality synthetic tabular data."
}