cs.CVDec 11, 2025

PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction

Authors: Brandon Smock, Maxim Sokolov, Libin Liang, Valerie Faucon-Morin, Amrit Ramesh, Tayyibah Khanam, Maury Courtland

Organizations: Kensho Technologies

Abstract

Table extraction (TE) is a key challenge in document understanding. Traditional approaches detect tables first, then recognize their structure. Recently, interest has surged in developing methods, such as vision-language models (VLMs), to extract tables directly in their full page or document context. However, a lack of annotated data has made progress difficult to demonstrate. To address this, we create a new large-scale dataset, PubTables-v2. PubTables-v2 unifies TE across various levels of surrounding context and, notably, is the first benchmark for multi-page TE. Our evaluations reveal that while current frontier models strongly outperform (+0.354 GriTSCon+0.354\ \textrm{GriTS}_\textrm{Con}) small models on the most complex task (full-document multi-page TE), this gap can be closed or even reversed (−0.056 GriTSCon-0.056\ \textrm{GriTS}_\textrm{Con}) on narrower tasks (cropped table extraction) with targeted training. Data is available at https://huggingface.co/datasets/kensho/PubTables-v2.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jun 8, 2026

POTATR: A Lightweight Image-to-Graph Model for Page-Level Table Extraction

Large-scale document processing requires contextually aware table extraction (TE) that is both accurate and efficient. Yet current approaches require billions of parameters, hundreds of autoregressive steps, or costly API inference. Motivated by this, we introduce the Page-Object Table Transformer (POTATR), a lightweight 29M parameter image-to-graph model that extends the Table Transformer (TATR) for contextualized page-level TE. POTATR outperforms all models tested on the PubTables-v2 Single Pages benchmark -- including frontier MLLMs -- achieving GriTSCon\textrm{GriTS}_\textrm{Con} of 0.964 while running over 130×\times faster at 300×\times lower cost. Further, POTATR's output is spatially grounded: every recognized element has a bounding box, enabling visual verification and geometric text assignment. As a result, POTATR performs unified page-level TE while composing with other models, enabling extension to scanned documents via external OCR and to full-document TE via techniques like cross-page merging. Code and models are available at https://github.com/kensho-technologies/POTATR.
Apr 21, 2026

PulseBench-Tab: A Multilingual Benchmark for Table Extraction with Graph-Based Evaluation

We introduce PulseBench-Tab, an open multilingual benchmark for evaluating table extraction from document images. The benchmark comprises 1,820 human-annotated tables spanning 9 languages and 4 scripts (Latin, CJK, Arabic, Cyrillic), drawn from 380 real-world source documents including financial filings, government reports, and regulatory disclosures. Tables range from 2 to 1,183 cells, with 48.1% containing merged or spanning cells. Alongside the dataset, we propose T-LAG (Table Logical Adjacency Graph), a novel evaluation metric that models tables as directed graphs over cell adjacencies and computes structural and content fidelity in a single score via optimal bipartite matching. We evaluate 9 commercial and open-source table extraction systems across the benchmark and report per-language breakdowns. The full dataset, scoring code, and all provider outputs are publicly available.
Jun 8, 2026

TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs

Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly evaluated on table reasoning tasks, but the role of table representation remains under-explored. In practice, the same table content may appear in different structural formats, such as HTML, Markdown, and LaTeX, or as rendered images. However, existing evaluations often let content, format, layout, and modality vary together, making it difficult to isolate representation effects. We introduce TABVERSE, a controlled multimodal table benchmark that aligns the same table content across multiple structural formats and rendered images, with question category and difficulty tags. This design enables systematic evaluation of representation effects while holding table content fixed. We evaluate LLMs and VLMs across three tasks: Question Answering (QA), Structural Understanding Capability (SUC), and Structure Reconstruction (SR). Our results show that representation choice substantially affects table understanding. Models generally perform better with structured text than with rendered images, but the size of this gap depends on the task, model, and format. HTML is often the most robust text format, while row-sensitive structural tasks and syntactically usable LaTeX reconstruction remain challenging. These findings show that table representation is a key factor in reliable table evaluation.