TABLET: A Large-Scale Dataset for Robust Visual Table Understanding

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Alonso, Iñigo, Miranda, Imanol, Agirre, Eneko, Lapata, Mirella
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911442895110144
author Alonso, Iñigo
Miranda, Imanol
Agirre, Eneko
Lapata, Mirella
author_facet Alonso, Iñigo
Miranda, Imanol
Agirre, Eneko
Lapata, Mirella
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21205
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TABLET: A Large-Scale Dataset for Robust Visual Table Understanding
Alonso, Iñigo
Miranda, Imanol
Agirre, Eneko
Lapata, Mirella
Computer Vision and Pattern Recognition
Computation and Language
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.
title TABLET: A Large-Scale Dataset for Robust Visual Table Understanding
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2509.21205