Saved in:
Bibliographic Details
Main Authors: Rao, Shihao, Li, Liang, Liu, Jiapeng, Lin, Tong, Li, Bing, Gao, Xiyan, Fu, Peng, Huang, Jing, Ma, Can
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2606.01936
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914622237310976
author Rao, Shihao
Li, Liang
Liu, Jiapeng
Lin, Tong
Li, Bing
Gao, Xiyan
Fu, Peng
Huang, Jing
Ma, Can
author_facet Rao, Shihao
Li, Liang
Liu, Jiapeng
Lin, Tong
Li, Bing
Gao, Xiyan
Fu, Peng
Huang, Jing
Ma, Can
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2606_01936
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle What to Format and How: A Benchmark and Workflow Approach for Document Formatting
Rao, Shihao
Li, Liang
Liu, Jiapeng
Lin, Tong
Li, Bing
Gao, Xiyan
Fu, Peng
Huang, Jing
Ma, Can
Computation and Language
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.
title What to Format and How: A Benchmark and Workflow Approach for Document Formatting
topic Computation and Language
url https://arxiv.org/abs/2606.01936