VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents

• URL: http://arxiv.org/abs/2603.15118v1
• Date: Mon, 16 Mar 2026 11:15:56 GMT
• Title: VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents
• Abstract summary: VAREX is a benchmark for evaluating structured data extraction from government forms.<n>The benchmark comprises 1,777 documents with 1,771 unique documents with validated ground truth through three-phase quality assurance.<n>Results reveal that below 4B parameters, compliance output -- not extraction capability -- is a dominant bottleneck.
• Score: 1.06378109904813
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce VAREX (VARied-schema EXtraction), a benchmark for evaluating multimodal foundation models on structured data extraction from government forms. VAREX employs a Reverse Annotation pipeline that programmatically fills PDF templates with synthetic values, producing deterministic ground truth validated through three-phase quality assurance. The benchmark comprises 1,777 documents with 1,771 unique schemas across three structural categories, each provided in four input modalities: plain text, layout-preserving text (whitespace-aligned to approximate column positions), document image, or both text and image combined. Unlike existing benchmarks that evaluate from a single input representation, VAREX provides four controlled modalities per document, enabling systematic ablation of how input format affects extraction accuracy -- a capability absent from prior benchmarks. We evaluate 20 models from frontier proprietary models to small open models, with particular attention to models <=4B parameters suitable for cost-sensitive and latency-constrained deployment. Results reveal that (1) below 4B parameters, structured output compliance -- not extraction capability -- is a dominant bottleneck; in particular, schema echo (models producing schema-conforming structure instead of extracted values) depresses scores by 45-65 pp (percentage points) in affected models; (2) extraction-specific fine-tuning at 2B yields +81 pp gains, demonstrating that the instruction-following deficit is addressable without scale; (3) layout-preserving text provides the largest accuracy gain (+3-18 pp), exceeding pixel-level visual cues; and (4) the benchmark most effectively discriminates models in the 60-95% accuracy band. Dataset and evaluation code are publicly available.

Related papers

• Visual Information Extraction from Documents via Classification-Guided Large Vision-Language Models [7.176656402971074]
  We propose a classification-guided large vision-language model (LVLM) framework for multi-type VIE that achieves high accuracy with minimal supervision.<n>The framework offers an efficient, scalable solution for complex document understanding in office automation.
  arXiv  Detail & Related papers  (2026-07-22T03:27:50Z)
• A Hybrid Vision-Language Architecture for Automated Defect Reasoning and Report Generation in Industrial Inspection [0.42970700836450487]
  This paper describes a decoupled, edge-deployable pipeline for wind turbine blade inspection.<n>The Eyes a Y26-x-obb oriented bounding-box localizes defects at dataset-native resolution.<n>The Bridge a deterministic, parameter-free encoding module maps each detected bounding box to grid-referenced tokens.
  arXiv  Detail & Related papers  (2026-05-26T04:27:38Z)
• Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization [54.749573452394664]
  We find that accuracy collapses as instance data grows, even when the formulation itself is simple.<n>We address this via a simple inference-time approach, BIND, which externalizes numeric data to structured files so the model binds data rather than from prompt prompt.<n>We validate our hypothesis by finetuning a model exclusively on binding and show that it outperforms end-to-end SFT and RL across three structurally distinct optimization categories.
  arXiv  Detail & Related papers  (2026-05-20T21:25:41Z)
• The Structured Output Benchmark: A Multi-Source Benchmark for Evaluating Structured Output Quality in Large Language Models [0.23332469289621785]
  We introduce SOB (The Structured Output Benchmark), a multi-source benchmark spanning three source modalities.<n>All models receive a text-normalized representation of their context regardless of source modality.<n>Our results reveal a consistent pattern: models achieve near-perfect schema compliance, yet the best Value Accuracy, measured by exact leaf-value match, reaches only 83.0% on text.
  arXiv  Detail & Related papers  (2026-04-28T08:27:01Z)
• LLM-based Schema-Guided Extraction and Validation of Missing-Person Intelligence from Heterogeneous Data Sources [0.7734726150561088]
  Missing-person and child-safety investigations rely on heterogeneous case documents, including structured forms, bulletin-style posters, and narrative web profiles.<n>Variations in layout, terminology, and data quality impede rapid triage, large-scale analysis, and search-planning.<n>This paper introduces the Guardian Pack, an AI-driven parsing and normalization pipeline that transforms multi-source investigative documents into a unified, schema-compliant representation.
  arXiv  Detail & Related papers  (2026-04-08T01:35:56Z)
• vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models [58.633451339058986]
  VLA models are typically evaluated using per benchmark scripts maintained independently by each model repository.<n>We present vla eval, an open source evaluation harness that decouples model inference from benchmark execution.<n>A complete evaluation requires only two commands: vla eval serve and vla eval run.
  arXiv  Detail & Related papers  (2026-03-14T14:38:53Z)
• Qianfan-OCR: A Unified End-to-End Model for Document Intelligence [41.67343426633923]
  Qianfan-OCR is an end-to-end vision-language model that unifies document parsing, layout analysis, and document understanding within a single architecture.<n>It performs direct image-to-Markdown conversion and supports diverse prompt-driven tasks including table extraction, chart understanding, document QA, and key information extraction.<n>It ranks first among end-to-end models on OmniDocBench v1.5 (93.12) and OlmOCR Bench (79.8), achieves competitive results on OCRBench, CCOCR, DocVQA, and ChartQA, and attains the highest average score on public key information extraction benchmarks
  arXiv  Detail & Related papers  (2026-03-11T16:08:22Z)
• ExtractBench: A Benchmark and Evaluation Methodology for Complex Structured Extraction [11.272127170490059]
  No end-to-end benchmark evaluates PDF-to-JSON extraction under enterprise-scale schema breadth.<n>No principled methodology captures the semantics of nested extraction.<n> ExtractBench is an open-source benchmark and evaluation framework for PDF-to-JSON structured extraction.
  arXiv  Detail & Related papers  (2026-02-12T18:31:37Z)
• Dripper: Token-Efficient Main HTML Extraction with a Lightweight LM [35.10225876152952]
  We present Dripper, an efficient HTML main content extraction framework powered by lightweight language models.<n>We introduce a controlled decoding mechanism that strictly constrains the output space through logits processors.<n>Dripper achieves state-of-the-art performance across all evaluation benchmarks and outperforms all baseline methods.
  arXiv  Detail & Related papers  (2025-11-28T12:04:46Z)
• 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)
• MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm [60.14048367611333]
  MonkeyOCR is a vision-language model for document parsing.<n>It advances the state of the art by leveraging a Structure-Recognition-Relation (SRR) triplet paradigm.
  arXiv  Detail & Related papers  (2025-06-05T16:34:57Z)
• Improving Embedding Accuracy for Document Retrieval Using Entity Relationship Maps and Model-Aware Contrastive Sampling [0.0]
  APEX-Embedding-7B is a 7-billion parameter decoder-only text Feature Extraction Model. Our approach employs two training techniques that yield an emergent improvement in factual focus. Based on our evaluations, our model establishes a new state-of-the-art standard in text feature extraction for longer context document retrieval tasks.
  arXiv  Detail & Related papers  (2024-10-08T17:36:48Z)
• ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction [51.87391234815163]
  E-commerce platforms require structured product data in the form of attribute-value pairs.<n>BERT-based extraction methods require large amounts of task-specific training data.<n>This paper explores using large language models (LLMs) as a more training-data efficient and robust alternative.
  arXiv  Detail & Related papers  (2023-10-19T07:39:00Z)
• How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources [117.6496550359768]
  This work explores recent advances in instruction-tuning language models on a range of open instruction-following datasets. We provide a large set of instruction-tuned models from 6.7B to 65B parameters in size, trained on 12 instruction datasets. We evaluate them on their factual knowledge, reasoning, multilinguality, coding, and open-ended instruction following abilities.
  arXiv  Detail & Related papers  (2023-06-07T19:59:23Z)

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.