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

• URL: http://arxiv.org/abs/2606.09578v1
• Date: Mon, 08 Jun 2026 14:52:46 GMT
• Title: TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs
• Abstract summary: Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly evaluated on table reasoning tasks.<n>We introduce TABVERSE, a controlled multimodal table benchmark that aligns the same table content across multiple structural formats.<n>Our results show that representation choice substantially affects table understanding.
• Score: 50.96120467118319
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Tables Decoded: DELTA for Structure, TARQA for Understanding [12.647289611255458]
  We present DELTA, which separates physical structure recognition, logical structure recognition, and OCR to extract both layout and content accurately.<n>On table structure recognition (TSR), DELTA TEDS- Structure scores comparable with state-of-the-art methods across FinTabNet, PubTabNet, and PubTables-1M.<n>Our approach yields gains of 9.3 p.p. on WTQ (TabQA) and 9.2 p.p. on FinTabNetQA (TabVQA), respectively.
  arXiv  Detail & Related papers  (2026-09-15T16:59:42Z)
• TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignment [70.83664203825235]
  TDATR (Table Detail-Aware Table Recognition) improves end-to-end TR through table detail-aware learning and cell-level visual alignment.<n>We achieve state-of-the-art or highly competitive performance on seven benchmarks without dataset-specific fine-tuning.
  arXiv  Detail & Related papers  (2026-03-24T05:45:02Z)
• Same Content, Different Representations: A Controlled Study for Table QA [15.896655757672441]
  Table Question Answering (Table QA) in real-world settings must operate over both structured databases and semi-structured tables containing textual fields.<n>Existing benchmarks are tied to fixed data formats and have not systematically examined how representation itself affects model performance.<n>We present the first controlled study that isolates the role of table representation by holding content constant while varying structure.
  arXiv  Detail & Related papers  (2025-09-26T22:33:19Z)
• TableDART: Dynamic Adaptive Multi-Modal Routing for Table Understanding [52.59372043981724]
  TableDART is a training-efficient framework that integrates multimodal views by reusing pretrained single-modality models.<n>In addition, we propose a novel agent to cross-modal knowledge integration by analyzing outputs from text- and image-based models.
  arXiv  Detail & Related papers  (2025-09-18T07:00:13Z)
• Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data [12.56716294438794]
  We investigate the effectiveness of both text-based and multimodal LLMs on table understanding tasks.<n>We compare their performance on tables from scientific vs. non-scientific contexts and examine their robustness on tables represented as images vs. text.
  arXiv  Detail & Related papers  (2025-06-30T18:04:36Z)
• Enhancing Large Vision-Language Models with Layout Modality for Table Question Answering on Japanese Annual Securities Reports [4.2134954427867]
  We propose a method to enhance LVLM-based table understanding by incorporating in-table textual content and layout features.<n> Experimental results demonstrate that these auxiliary modalities significantly improve performance.
  arXiv  Detail & Related papers  (2025-05-23T08:36:22Z)
• Texts or Images? A Fine-grained Analysis on the Effectiveness of Input Representations and Models for Table Question Answering [16.790216473975146]
  We conduct the first controlled study on the effectiveness of several combinations of table representations and models from two perspectives.<n>We find that the best combination of table representation and model varies across setups.<n>We propose FRES, a method selecting table representations dynamically, and observe a 10% average performance improvement.
  arXiv  Detail & Related papers  (2025-05-20T09:36:17Z)
• PixT3: Pixel-based Table-To-Text Generation [66.96636025277536]
  We present PixT3, a multimodal table-to-text model that overcomes the challenges of linearization and input size limitations. Experiments on the ToTTo and Logic2Text benchmarks show that PixT3 is competitive and superior to generators that operate solely on text.
  arXiv  Detail & Related papers  (2023-11-16T11:32:47Z)
• SEMv2: Table Separation Line Detection Based on Instance Segmentation [96.36188168694781]
  We propose an accurate table structure recognizer, termed SEMv2 (SEM: Split, Embed and Merge) We address the table separation line instance-level discrimination problem and introduce a table separation line detection strategy based on conditional convolution. To comprehensively evaluate the SEMv2, we also present a more challenging dataset for table structure recognition, dubbed iFLYTAB.
  arXiv  Detail & Related papers  (2023-03-08T05:15:01Z)
• Table Retrieval May Not Necessitate Table-specific Model Design [83.27735758203089]
  We focus on the task of table retrieval, and ask: "is table-specific model design necessary for table retrieval?" Based on an analysis on a table-based portion of the Natural Questions dataset (NQ-table), we find that structure plays a negligible role in more than 70% of the cases. We then experiment with three modules to explicitly encode table structures, namely auxiliary row/column embeddings, hard attention masks, and soft relation-based attention biases. None of these yielded significant improvements, suggesting that table-specific model design may not be necessary for table retrieval.
  arXiv  Detail & Related papers  (2022-05-19T20:35:23Z)
• Retrieving Complex Tables with Multi-Granular Graph Representation Learning [20.72341939868327]
  The task of natural language table retrieval seeks to retrieve semantically relevant tables based on natural language queries. Existing learning systems treat tables as plain text based on the assumption that tables are structured as dataframes. We propose Graph-based Table Retrieval (GTR), a generalizable NLTR framework with multi-granular graph representation learning.
  arXiv  Detail & Related papers  (2021-05-04T20:19:03Z)
• A Graph Representation of Semi-structured Data for Web Question Answering [96.46484690047491]
  We propose a novel graph representation of Web tables and lists based on a systematic categorization of the components in semi-structured data as well as their relations. Our method improves F1 score by 3.90 points over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-10-14T04:01:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.