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 this http URL 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 this http URL 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.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2606.01936 [cs.CL] |
| (or arXiv:2606.01936v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.01936 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Liang Li [view email]
[v1]
Mon, 1 Jun 2026 09:02:33 UTC (1,016 KB)