DTBench: A Synthetic Benchmark for Document-to-Table Extraction

• URL: http://arxiv.org/abs/2602.13812v2
• Date: Tue, 17 Feb 2026 15:46:12 GMT
• Title: DTBench: A Synthetic Benchmark for Document-to-Table Extraction
• Authors: Yuxiang Guo, Zhuoran Du, Nan Tang, Kezheng Tang, Congcong Ge, Yunjun Gao,
• Abstract summary: Document-to-table (Doc2Table) extraction derives structured tables from unstructured documents under a target schema.<n>Existing benchmarks neither explicitly distinguish nor comprehensively cover the diverse capabilities required in Doc2Table extraction.<n>We present DTBench, a synthetic benchmark that adopts a proposed two-level taxonomy of Doc2Table capabilities.
• Score: 19.499877109720945
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Document-to-table (Doc2Table) extraction derives structured tables from unstructured documents under a target schema, enabling reliable and verifiable SQL-based data analytics. Although large language models (LLMs) have shown promise in flexible information extraction, their ability to produce precisely structured tables remains insufficiently understood, particularly for indirect extraction that requires complex capabilities such as reasoning and conflict resolution. Existing benchmarks neither explicitly distinguish nor comprehensively cover the diverse capabilities required in Doc2Table extraction. We argue that a capability-aware benchmark is essential for systematic evaluation. However, constructing such benchmarks using human-annotated document-table pairs is costly, difficult to scale, and limited in capability coverage. To address this, we adopt a reverse Table2Doc paradigm and design a multi-agent synthesis workflow to generate documents from ground-truth tables. Based on this approach, we present DTBench, a synthetic benchmark that adopts a proposed two-level taxonomy of Doc2Table capabilities, covering 5 major categories and 13 subcategories. We evaluate several mainstream LLMs on DTBench, and demonstrate substantial performance gaps across models, as well as persistent challenges in reasoning, faithfulness, and conflict resolution. DTBench provides a comprehensive testbed for data generation and evaluation, facilitating future research on Doc2Table extraction. The benchmark is publicly available at https://github.com/ZJU-DAILY/DTBench.

Related papers

• ExStrucTiny: A Benchmark for Schema-Variable Structured Information Extraction from Document Images [19.490609860018804]
  We introduce ExStrucTiny, a new benchmark dataset for structured Information Extraction (IE) from document images.<n>Built through a novel pipeline combining manual and synthetic human-validated samples, ExStrucTiny covers more varied document types and extraction scenarios.<n>We analyze open and closed Vision Language Models on this benchmark, highlighting challenges such as adaptation, query under-specification, and schema adaptation.
  arXiv  Detail & Related papers  (2026-02-12T17:38:57Z)
• MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns [80.05126590825121]
  MonkeyOCR v1.5 is a unified vision-language framework that enhances both layout understanding and content recognition.<n>To address complex table structures, we propose a visual consistency-based reinforcement learning scheme.<n>Two specialized modules, Image-Decoupled Table Parsing and Type-Guided Table Merging, are introduced to enable reliable parsing of tables.
  arXiv  Detail & Related papers  (2025-11-13T15:12:17Z)
• From Surface to Semantics: Semantic Structure Parsing for Table-Centric Document Analysis [9.526986293067576]
  DOTABLER is a table-centric semantic document parsing framework.<n>It delivers comprehensive table-anchored semantic analysis and precise extraction of semantically relevant tables.<n> evaluated on nearly 4,000 pages with over 1,000 tables from real-world PDFs.
  arXiv  Detail & Related papers  (2025-08-14T03:29:51Z)
• Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction [80.88654868264645]
  Arranged and Organized Extraction Benchmark designed to evaluate ability of large language models to comprehend fragmented documents.<n>AOE includes 11 carefully crafted tasks across three diverse domains, requiring models to generate context-specific schema tailored to varied input queries.<n>Results show that even the most advanced models struggled significantly.
  arXiv  Detail & Related papers  (2025-07-22T06:37:51Z)
• ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models [58.34560740973768]
  We introduce a framework that leverages language models (LMs) to generate literature review tables. A new dataset of 2,228 literature review tables extracted from ArXiv papers synthesize a total of 7,542 research papers. We evaluate LMs' abilities to reconstruct reference tables, finding this task benefits from additional context.
  arXiv  Detail & Related papers  (2024-10-25T18:31:50Z)
• REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking [11.374031643273941]
  REXEL is a highly efficient and accurate model for the joint task of document level cIE (DocIE) It is on average 11 times faster than competitive existing approaches in a similar setting. The combination of speed and accuracy makes REXEL an accurate cost-efficient system for extracting structured information at web-scale.
  arXiv  Detail & Related papers  (2024-04-19T11:04:27Z)
• Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs [79.0426838808629]
  We propose TAT-DQA, i.e. to answer the question over a visually-rich table-text document. Specifically, we propose a novel Doc2SoarGraph framework with enhanced discrete reasoning capability. We conduct extensive experiments on TAT-DQA dataset, and the results show that our proposed framework outperforms the best baseline model by 17.73% and 16.91% in terms of Exact Match (EM) and F1 score respectively on the test set.
  arXiv  Detail & Related papers  (2023-05-03T07:30:32Z)
• 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)
• Document-Level Relation Extraction with Sentences Importance Estimation and Focusing [52.069206266557266]
  Document-level relation extraction (DocRE) aims to determine the relation between two entities from a document of multiple sentences. We propose a Sentence Estimation and Focusing (SIEF) framework for DocRE, where we design a sentence importance score and a sentence focusing loss. Experimental results on two domains show that our SIEF not only improves overall performance, but also makes DocRE models more robust.
  arXiv  Detail & Related papers  (2022-04-27T03:20:07Z)

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.