Tables Decoded: DELTA for Structure, TARQA for Understanding

• URL: http://arxiv.org/abs/2609.17458v1
• Date: Tue, 15 Sep 2026 16:59:42 GMT
• Title: Tables Decoded: DELTA for Structure, TARQA for Understanding
• Abstract summary: 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.
• Score: 12.647289611255458
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering (TabVQA). While recent approaches predominantly rely on vision- language models (VLMs) operating on table images, we propose a more scalable and effective alternative based on structured textual representations. These representations are easier to process, align more naturally with LLMs, and eliminate the need for language-specific visual encoders, making them particularly suitable for multilingual documents. We present DELTA, which separates physical structure recognition, logical structure recognition, and OCR to extract both layout and content accurately. DELTA outputs tables in Optimised Table Structure Language (OTSL), a compact and unified format that encodes cell arrangements and textual content. On table structure recognition (TSR), DELTA achieves TEDS- Structure scores comparable with state-of-the-art methods across FinTabNet, PubTabNet, and PubTables-1M. We further establish its robustness on non-English tables through our curated Hindi benchmark, TORQUE. Building on this, we introduce TARQA, an LLM fine-tuned on OTSL sequences. Our approach yields gains of 9.3 p.p. on WTQ (TabQA) and 9.2 p.p. on FinTabNetQA (TabVQA), respectively. On TORQUE, our method ranks second among all VLMs and DELTA + LLM variants. We release our code, models, and benchmark at: https://github.com/Tihiitborg/Tables-Decoded

Related papers

• DeepTable: Structural Attention Biases and Tree Path Encoding for Hierarchical Table Understanding [10.761232681902394]
  Large language models (LLMs) have demonstrated strong performance in table understanding.<n>We propose DeepTable, a structure-aware approach for table understanding with LLMs.
  arXiv  Detail & Related papers  (2026-09-07T16:19:33Z)
• TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs [50.96120467118319]
  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.
  arXiv  Detail & Related papers  (2026-06-08T14:52:46Z)
• DenTab: A Dataset for Table Recognition and Visual QA on Real-World Dental Estimates [2.7885016877286897]
  DenTab is a dataset of 2,000 cropped table images from dental estimates with high-quality HTML annotations.<n>We benchmark 16 systems, including 14 vision-language executor models (VLMs) and two OCR baselines.<n>We propose the Table Router Pipeline, which routes arithmetic questions to deterministic execution.
  arXiv  Detail & Related papers  (2026-04-17T14:33:51Z)
• 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)
• 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)
• SPRINT: Script-agnostic Structure Recognition in Tables [20.394597266150534]
  Table Structure Recognition (TSR) is vital for various downstream tasks like information retrieval, table reconstruction, and document understanding.<n>We propose TSR as a language-agnostic cell arrangement prediction and introduce SPRINT, Script-agnostic Structure Recognition in Tables.<n>We experimentally evaluate our performance across benchmark TSR datasets including PubTabNet, FinTabNet, and PubTables-1M.
  arXiv  Detail & Related papers  (2025-03-15T00:43:53Z)
• UniTabNet: Bridging Vision and Language Models for Enhanced Table Structure Recognition [55.153629718464565]
  We introduce UniTabNet, a novel framework for table structure parsing based on the image-to-text model. UniTabNet employs a divide-and-conquer'' strategy, utilizing an image-to-text model to decouple table cells and integrating both physical and logical decoders to reconstruct the complete table structure.
  arXiv  Detail & Related papers  (2024-09-20T01:26:32Z)
• Multimodal Table Understanding [26.652797853893233]
  How to directly understand tables using intuitive visual information is a crucial and urgent challenge for developing more practical applications. We propose a new problem, multimodal table understanding, where the model needs to generate correct responses to various table-related requests. We develop Table-LLaVA, a generalist multimodal large language model (MLLM), which significantly outperforms recent open-source MLLM baselines on 23 benchmarks.
  arXiv  Detail & Related papers  (2024-06-12T11:27:03Z)
• Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study [44.39031420687302]
  Large language models (LLMs) are becoming attractive as few-shot reasoners to solve Natural Language (NL)-related tasks. We try to understand this by designing a benchmark to evaluate the structural understanding capabilities of LLMs. We propose $textitself-augmentation$ for effective structural prompting, such as critical value / range identification.
  arXiv  Detail & Related papers  (2023-05-22T14:23:46Z)
• 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)
• GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing [117.98107557103877]
  We present GraPPa, an effective pre-training approach for table semantic parsing. We construct synthetic question-pairs over high-free tables via a synchronous context-free grammar. To maintain the model's ability to represent real-world data, we also include masked language modeling.
  arXiv  Detail & Related papers  (2020-09-29T08:17:58Z)

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.