{"ID":2866053,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21205","arxiv_id":"2509.21205","title":"TABLET: A Large-Scale Dataset for Robust Visual Table Understanding","abstract":"While table understanding increasingly relies on pixel-only settings, current benchmarks predominantly use synthetic renderings that lack the complexity and visual diversity of real-world tables. Additionally, existing visual table understanding (VTU) datasets offer fixed examples with single visualizations and pre-defined instructions, providing no access to underlying serialized data for reformulation. We introduce TABLET, a large-scale VTU dataset with 4 million examples across 21 tasks, grounded in 2 million unique tables where 88% preserve original visualizations. To evaluate whether models are able to jointly reason over tabular and visual content, we also introduce VisualTableQA, a benchmark requiring both visual perception and table understanding. Fine-tuning vision-language models like Qwen2.5-VL-7B and Gemma 3-4B on TABLET improves performance on seen and unseen VTU tasks while increasing robustness on real-world table visualizations. By preserving original visualizations and maintaining example traceability in a unified large-scale collection, TABLET establishes a foundation for robust training and extensible evaluation of future VTU models.","short_abstract":"While table understanding increasingly relies on pixel-only settings, current benchmarks predominantly use synthetic renderings that lack the complexity and visual diversity of real-world tables. Additionally, existing visual table understanding (VTU) datasets offer fixed examples with single visualizations and pre-def...","url_abs":"https://arxiv.org/abs/2509.21205","url_pdf":"https://arxiv.org/pdf/2509.21205v3","authors":"[\"Iñigo Alonso\",\"Imanol Miranda\",\"Eneko Agirre\",\"Mirella Lapata\"]","published":"2025-09-25T14:14:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false}