What to Format and How: A Benchmark and Workflow Approach for Document Formatting

• URL: http://arxiv.org/abs/2606.01936v1
• Date: Mon, 01 Jun 2026 09:02:33 GMT
• Title: What to Format and How: A Benchmark and Workflow Approach for Document Formatting
• Abstract summary: Real-world formatting often requires identifying targets based on document content.<n>We introduce DocFormBench, a benchmark that extends Text-to-Format evaluation to diverse formats.<n>We propose DocFormFlow, a method that decouples target localization from modification execution into what to format and how.
• Score: 25.500100602233076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in large language models (LLMs) have opened up new possibilities for automated document formatting. However, real-world formatting often requires identifying targets based on document content. This content-aware setting remains challenging and underexplored, primarily due to the lack of dedicated evaluation datasets.To enable evaluation in realistic content-aware scenarios, we introduce DocFormBench, a benchmark that extends Text-to-Format evaluation to diverse formatting requirements, along with metrics for both accuracy and efficiency.To mitigate redundant document reading in existing methods during formatting, we propose DocFormFlow, a workflow formatting method that decouples target localization from modification execution into what to format and how. Extensive experiments across multiple LLMs and multimodal models show that DocFormFlow consistently improves formatting accuracy while reducing token consumption compared to representative baselines. Further analysis reveals that precise target localization is the primary factor influencing formatting performance. We hope DocFormBench and DocFormFlow will facilitate future research toward more intelligent and reliable document formatting.

Related papers

• Not as Sweet by Another Name: An Empirical Study of Format Robustness in LLM Document Workflows [19.259315558139573]
  We conduct a large-scale empirical study spanning four representative tasks, four real-world tasks, and four document formats.<n>Our findings reveal that format variation poses a systematic and serious threat.<n>Our study demonstrates that document format is not a neutral wrapper but a critical factor affecting the reliability of LLM systems.
  arXiv  Detail & Related papers  (2026-07-30T03:59:42Z)
• UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters [55.34921520578968]
  Vision-language models (VLMs) have achieved impressive unified recognition of text and formulas.<n>We propose UniRec-0.1B, a unified recognition model with only 0.1B parameters.<n>It is capable of performing text and formula recognition at multiple levels, including characters, words, lines, paragraphs, and documents.
  arXiv  Detail & Related papers  (2025-12-24T10:35:21Z)
• FlexDoc: Parameterized Sampling for Diverse Multilingual Synthetic Documents for Training Document Understanding Models [4.013756026582041]
  Developing document understanding models at enterprise scale requires large, diverse, and well-annotated datasets.<n>We introduce FlexDoc, a scalable synthetic data generation framework.<n>We show that FlexDoc improves the absolute F1 Score by up to 11% when used to augment real datasets.
  arXiv  Detail & Related papers  (2025-10-02T15:42:35Z)
• DocSpiral: A Platform for Integrated Assistive Document Annotation through Human-in-the-Spiral [11.336757553731639]
  Acquiring structured data from domain-specific, image-based documents is crucial for many downstream tasks.<n>Many documents exist as images rather than as machine-readable text, which requires human annotation to train automated extraction systems.<n>We present DocSpiral, the first Human-in-the-Spiral assistive document annotation platform.
  arXiv  Detail & Related papers  (2025-05-06T06:02:42Z)
• LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs [69.40865293066885]
  We present the first systematic evaluation examining format bias in performance of large language models (LLMs)<n>We present our empirical format bias evaluation spanning four commonly used categories -- multiple-choice question-answer, wrapping, list, and mapping.
  arXiv  Detail & Related papers  (2024-08-16T10:45:45Z)
• Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting [68.19544657508509]
  Large language models (LLMs) are adopted as a fundamental component of language technologies. We find that several widely used open-source LLMs are extremely sensitive to subtle changes in prompt format in few-shot settings. We propose an algorithm that rapidly evaluates a sampled set of plausible prompt formats for a given task, and reports the interval of expected performance without accessing model weights.
  arXiv  Detail & Related papers  (2023-10-17T15:03:30Z)
• 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)
• Unified Pretraining Framework for Document Understanding [52.224359498792836]
  We present UDoc, a new unified pretraining framework for document understanding. UDoc is designed to support most document understanding tasks, extending the Transformer to take multimodal embeddings as input. An important feature of UDoc is that it learns a generic representation by making use of three self-supervised losses.
  arXiv  Detail & Related papers  (2022-04-22T21:47:04Z)
• Value Retrieval with Arbitrary Queries for Form-like Documents [50.5532781148902]
  We propose value retrieval with arbitrary queries for form-like documents. Our method predicts target value for an arbitrary query based on the understanding of layout and semantics of a form. We propose a simple document language modeling (simpleDLM) strategy to improve document understanding on large-scale model pre-training.
  arXiv  Detail & Related papers  (2021-12-15T01:12:02Z)

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.