Layout-Aware Text Editing for Efficient Transformation of Academic PDFs to Markdown

• URL: http://arxiv.org/abs/2512.18115v1
• Date: Fri, 19 Dec 2025 22:43:12 GMT
• Title: Layout-Aware Text Editing for Efficient Transformation of Academic PDFs to Markdown
• Abstract summary: Academic documents stored in PDF format can be transformed into plain text structured markup languages.<n>We introduce EditTrans, a hybrid editing-generation model whose features allow identifying a queue of to-be-edited text from a PDF before starting to generate markup language.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Academic documents stored in PDF format can be transformed into plain text structured markup languages to enhance accessibility and enable scalable digital library workflows. Markup languages allow for easier updates and customization, making academic content more adaptable and accessible to diverse usage, such as linguistic corpus compilation. Such documents, typically delivered in PDF format, contain complex elements including mathematical formulas, figures, headers, and tables, as well as densely layouted text. Existing end-to-end decoder transformer models can transform screenshots of documents into markup language. However, these models exhibit significant inefficiencies; their token-by-token decoding from scratch wastes a lot of inference steps in regenerating dense text that could be directly copied from PDF files. To solve this problem, we introduce EditTrans, a hybrid editing-generation model whose features allow identifying a queue of to-be-edited text from a PDF before starting to generate markup language. EditTrans contains a lightweight classifier fine-tuned from a Document Layout Analysis model on 162,127 pages of documents from arXiv. In our evaluations, EditTrans reduced the transformation latency up to 44.5% compared to end-to-end decoder transformer models, while maintaining transformation quality. Our code and reproducible dataset production scripts are open-sourced.

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)
• MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing [74.84107522458798]
  MPDocBench-Parse is a benchmark for multi-page document parsing in real-world applications.<n>It contains 433 manually annotated documents with 3,246 pages, covering 15 document types in English and Chinese, with diverse layout styles.
  arXiv  Detail & Related papers  (2026-05-21T07:36:41Z)
• ForMaT: Dataset for Visually-Grounded Multilingual PDF Translation [0.27998963147546146]
  We present ForMaT (Format-Preserving Multilingual Translation), a parallel corpus of 3,956 PDFs across 15 language pairs.<n>We employ K-Medoids sampling over 45 geometric features, capturing complex elements like nested tables and formulas to focus only on visually diverse PDF documents.
  arXiv  Detail & Related papers  (2026-05-15T09:50:37Z)
• BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation [9.979324579114392]
  Existing document translation pipelines face a tension between linguistic processing and layout preservation.<n>We introduce BabelDOC, an Intermediate Representation (IR)-based framework for layout-preserving PDF translation.<n>BabelDOC decouples visual layout metadata from semantic content, enabling document-level translation operations.
  arXiv  Detail & Related papers  (2026-05-11T16:56:44Z)
• CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layers [48.779823303618734]
  We propose a hybrid generative framework for rendering graphic design parsing.<n>It decomposes a design image into editable text, background, and sticker layers.<n>Text regions are parsed using a vision-language model into a text design protocol.<n>Background sticker layers are generated using a multi-branch diffusion architecture.
  arXiv  Detail & Related papers  (2026-04-21T16:20:19Z)
• PDFInspect: A Unified Feature Extraction Framework for Malicious Document Detection [0.0]
  This work presents a unified framework that integrates graph-based, structural, and metadata-driven analysis to generate a rich feature representation for each PDF document.<n>The proposed approach is scalable,170, and designed to support real-world PDF threat intelligence.
  arXiv  Detail & Related papers  (2026-01-19T09:23:40Z)
• Detecting Post-generation Edits to Watermarked LLM Outputs via Combinatorial Watermarking [51.417096446156926]
  We introduce a new task: detecting post-generation edits locally made to watermarked LLM outputs.<n>We propose a pattern-based watermarking framework, which partitions the vocabulary into disjoint subsets and embeds the watermark.<n>We evaluate our method on open-source LLMs across a variety of editing scenarios, demonstrating strong empirical performance in edit localization.
  arXiv  Detail & Related papers  (2025-10-02T03:33:12Z)
• WGRAMMAR: Leverage Prior Knowledge to Accelerate Structured Decoding [58.1177179119881]
  We introduce wgrammar, a lightweight decoding engine that integrates domain-aware simplification, constraint decomposition, and mask caching.<n> wgrammar achieves up to 250x speedup over existing systems.
  arXiv  Detail & Related papers  (2025-07-22T17:13:47Z)
• EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering [9.087419148444225]
  This paper introduces EasyText, a text rendering framework based on DiT (Diffusion Transformer)<n>We propose character positioning encoding and position encoding techniques to achieve controllable and precise text rendering.<n>We construct a large-scale synthetic text image dataset with 1 million multilingual image-text annotations as well as a high-quality dataset of 20K annotated images.
  arXiv  Detail & Related papers  (2025-05-30T09:55:39Z)
• olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models [16.470130668266055]
  olmOCR is an open-source toolkit for processing PDFs into clean, linearized plain text in natural reading order.<n> olmOCR is optimized for large-scale batch processing, able to scale flexibly to different hardware setups.<n>We find olmOCR outperforms even top vision language models including GPT-4o, Gemini Flash 2 and Qwen-2.5-VL.
  arXiv  Detail & Related papers  (2025-02-25T18:38:38Z)
• Discourse Features Enhance Detection of Document-Level Machine-Generated Content [53.41994768824785]
  Machine-generated content poses challenges such as academic plagiarism and the spread of misinformation.<n>Existing MGC detectors often focus solely on surface-level information, overlooking implicit and structural features.<n>We introduce novel methodologies and datasets to overcome these challenges.
  arXiv  Detail & Related papers  (2024-12-17T08:47:41Z)
• PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling [63.93112754821312]
  Multimodal document understanding is a challenging task to process and comprehend large amounts of textual and visual information.<n>Recent advances in Large Language Models (LLMs) have significantly improved the performance of this task.<n>We introduce PDF-WuKong, a multimodal large language model (MLLM) which is designed to enhance multimodal question-answering (QA) for long PDF documents.
  arXiv  Detail & Related papers  (2024-10-08T12:17:42Z)
• WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data [13.297444760076406]
  We introduce WordScape, a novel pipeline for the creation of cross-disciplinary, multilingual corpora. WordScape parses the Open XML structure of Word documents obtained from the web. It offers culturally and linguistically diverse document pages with natural semantic structure and high-quality text.
  arXiv  Detail & Related papers  (2023-12-15T20:28:31Z)
• SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pages [87.08880616654258]
  We introduce the SWiPE dataset, which reconstructs the document-level editing process from English Wikipedia (EW) articles to paired Simple Wikipedia (SEW) articles. We work with Wikipedia editors to annotate 5,000 EW-SEW document pairs, labeling more than 40,000 edits with proposed 19 categories. We find that SWiPE-trained models generate more complex edits while reducing unwanted edits.
  arXiv  Detail & Related papers  (2023-05-30T16:52:42Z)
• XDoc: Unified Pre-training for Cross-Format Document Understanding [84.63416346227176]
  XDoc is a unified pre-trained model which deals with different document formats in a single model. XDoc achieves comparable or even better performance on a variety of downstream tasks compared with the individual pre-trained models.
  arXiv  Detail & Related papers  (2022-10-06T12:07:18Z)
• Automatic Document Sketching: Generating Drafts from Analogous Texts [44.626645471195495]
  We introduce a new task, document sketching, which involves generating entire draft documents for the writer to review and revise. These drafts are built from sets of documents that overlap in form - sharing large segments of potentially reusable text - while diverging in content. We investigate the application of weakly supervised methods, including use of a transformer-based mixture of experts, together with reinforcement learning.
  arXiv  Detail & Related papers  (2021-06-14T06:46:06Z)
• Robust PDF Document Conversion Using Recurrent Neural Networks [0.0]
  We present a novel approach to document structure recovery in PDF using recurrent neural networks. We show how a sequence of PDF printing commands can be used as input into a neural network. We implement a model that yields a weighted average F1 score of 97% across 17 distinct structural labels.
  arXiv  Detail & Related papers  (2021-02-18T14:39:54Z)
• Text Editing by Command [82.50904226312451]
  A prevailing paradigm in neural text generation is one-shot generation, where text is produced in a single step. We address this limitation with an interactive text generation setting in which the user interacts with the system by issuing commands to edit existing text. We show that our Interactive Editor, a transformer-based model trained on this dataset, outperforms baselines and obtains positive results in both automatic and human evaluations.
  arXiv  Detail & Related papers  (2020-10-24T08:00:30Z)

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.