TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction

• URL: http://arxiv.org/abs/2604.22880v1
• Date: Fri, 24 Apr 2026 03:34:06 GMT
• Title: TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction
• Abstract summary: We study page-level reconstruction of scientific PDFs into compilable and introduce TexOCR-Bench and TexOCR-Train.<n> TexOCR-Bench features a multi-dimensional evaluation suite that jointly assesses transcription fidelity, structural faithfulness, and end-to-end compilability.<n>Our analysis further reveals that RL with verifiable rewards yields consistent improvements over SFT alone.
• Score: 18.280524101821452
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing document OCR largely targets plain text or Markdown, discarding the structural and executable properties that make LaTeX essential for scientific publishing. We study page-level reconstruction of scientific PDFs into compilable LaTeX and introduce TexOCR-Bench, a benchmark, and TexOCR-Train, a large-scale training corpus, for this task. TexOCR-Bench features a multi-dimensional evaluation suite that jointly assesses transcription fidelity, structural faithfulness, and end-to-end compilability. Leveraging TexOCR-Train, we train a 2B-parameter model, TexOCR, using supervised fine-tuning (SFT) and reinforcement learning (RL) with verifiable rewards derived from LaTeX unit tests that directly enforce compilability and referential integrity. Experiments across 21 frontier models on TexOCR-Bench show that existing systems frequently violate key document invariants, including consistent section structure, correct float placement, and valid label-reference links, which undermines compilation reliability and downstream usability. Our analysis further reveals that RL with verifiable rewards yields consistent improvements over SFT alone, particularly on structural and compilation metrics.

Related papers

• Code as Representation: A Compilable Parsing Paradigm for Academic Documents [50.40789738182074]
  Compilable Academic Document Parsing (CADP) is a paradigm that reconstructs a full page as contextual La plus executable Python.<n>We introduce CADP-Bench, an expert-verified benchmark of full academic pages containing text and multiple SAE types.<n>Results show that even frontier models still struggle to produce high-fidelity executable reconstructions.
  arXiv  Detail & Related papers  (2026-08-18T09:10:43Z)
• TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documents [50.64307290680222]
  TongGuOCR is a layout-aware and token-augmented multimodal large language model (MLLM) for OCR of Chinese historical documents.<n>TongGuOCR achieves 93.76 AR and reduces NED from 10.43 to 6.15 and RO-ED from 7.53 to 3.49 relative to the best competing score for each metric.
  arXiv  Detail & Related papers  (2026-08-08T04:50:00Z)
• 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)
• Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models [53.03670032402846]
  We address the task of table image to code generation, with the goal of automating the reconstruction of high-quality, publication-ready tables from visual inputs.<n>A central challenge of this task lies in accurately handling complex tables -- those with large sizes, deeply nested structures, and semantically rich or irregular cell content.<n>We propose a reinforced multimodal large language model (MLLM) framework, where a pre-trained MLLM is fine-tuned on a large-scale table-to-La dataset.
  arXiv  Detail & Related papers  (2025-09-22T11:13:48Z)
• LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination [46.53643691093418]
  We introduce MTTrans, a collaborative multi-agent system designed to translate structured-formatted documents.<n>Trans ensures format preservation, structural fidelity, and consistency through six specialized agents.
  arXiv  Detail & Related papers  (2025-08-26T08:17:26Z)
• TeXpert: A Multi-Level Benchmark for Evaluating LaTeX Code Generation by LLMs [0.0]
  Large Language Models (LLMs) present a promising opportunity for researchers to produce publication-ready material.<n>Our benchmark dataset with natural language prompts for generating code focused on components of scientific documents.<n>Our evaluation across open and closed-source LLMs highlights multiple key findings.
  arXiv  Detail & Related papers  (2025-06-20T13:39:16Z)
• VISTA-OCR: Towards generative and interactive end to end OCR models [3.7548609506798494]
  VISTA-OCR is a lightweight architecture that unifies text detection and recognition within a single generative model.<n>Built on an encoder-decoder architecture, VISTA-OCR is progressively trained, starting with the visual feature extraction phase.<n>To enhance the model's capabilities, we built a new dataset composed of real-world examples enriched with bounding box annotations and synthetic samples.
  arXiv  Detail & Related papers  (2025-04-04T17:39:53Z)
• LOCR: Location-Guided Transformer for Optical Character Recognition [55.195165959662795]
  We propose LOCR, a model that integrates location guiding into the transformer architecture during autoregression. We train the model on a dataset comprising over 77M text-location pairs from 125K academic document pages, including bounding boxes for words, tables and mathematical symbols. It outperforms all existing methods in our test set constructed from arXiv, as measured by edit distance, BLEU, METEOR and F-measure.
  arXiv  Detail & Related papers  (2024-03-04T15:34:12Z)
• Distilling Text Style Transfer With Self-Explanation From LLMs [28.595450029172124]
  Text Style Transfer (TST) seeks to alter the style of text while retaining its core content. We propose a framework that leverages large language models (LLMs) alongside chain-of-thought (CoT) Co is shown to surpass traditional supervised fine-tuning and knowledge distillation methods.
  arXiv  Detail & Related papers  (2024-03-02T06:38:15Z)

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.