@inproceedings{onderkova-etal-2025-freshtab,
    title = "{F}resh{T}ab: Sourcing Fresh Data for Table-to-Text Generation Evaluation",
    author = "Onderkov{\'a}, Krist{\'y}na  and
      Platek, Ondrej  and
      Kasner, Zden{\v{e}}k  and
      Dusek, Ondrej",
    editor = "Flek, Lucie  and
      Narayan, Shashi  and
      Phương, L{\^e} Hồng  and
      Pei, Jiahuan",
    booktitle = "Proceedings of the 18th International Natural Language Generation Conference",
    month = oct,
    year = "2025",
    address = "Hanoi, Vietnam",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-you-zhang-rochester/2025.inlg-main.7/",
    pages = "108--121",
    abstract = "Table-to-text generation (insight generation from tables) is a challenging task that requires precision in analyzing the data. In addition, the evaluation of existing benchmarks is affected by contamination of Large Language Model (LLM) training data as well as domain imbalance. We introduce FreshTab, an on-the-fly table-to-text benchmark generation from Wikipedia, to combat the LLM data contamination problem and enable domain-sensitive evaluation. While non-English table-to-text datasets are limited, FreshTab collects datasets in different languages on demand (we experiment with German, Russian and French in addition to English). We find that insights generated by LLMs from recent tables collected by our method appear clearly worse by automatic metrics, but this does not translate into LLM and human evaluations. Domain effects are visible in all evaluations, showing that a domain-balanced benchmark is more challenging."
}