What to Format and How: A Benchmark and Workflow Approach for Document Formatting
2026-06-01 • Computation and Language
Computation and Language
AI summaryⓘ
The authors created a new test called DocFormBench to check how well computers can format documents by understanding their content. They also made a new method, DocFormFlow, that helps the computer decide what parts of the document to change and how to change them, making the process more accurate and efficient. Their experiments showed that finding the right parts of the document to change is very important for good formatting. This work aims to help future research make document formatting smarter and more reliable.
large language modelsdocument formattingcontent-aware processingbenchmark datasettarget localizationworkflow methodtoken consumptionmultimodal modelsformatting accuracyautomated document editing
Authors
Shihao Rao, Liang Li, Jiapeng Liu, Tong Lin, Bing Li, Xiyan Gao, Peng Fu, Jing Huang, Can Ma
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.