Papers
arxiv:2510.11391

DocReward: A Document Reward Model for Structuring and Stylizing

Published on Oct 13
ยท Submitted by Junpeng Liu on Oct 14
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,

Abstract

DocReward, a document reward model, evaluates and enhances the structural and stylistic quality of generated documents, outperforming GPT-4o and GPT-5 in both accuracy and human-preferred document generation.

AI-generated summary

Recent advances in agentic workflows have enabled the automation of tasks such as professional document generation. However, they primarily focus on textual quality, neglecting visual structure and style, which are crucial for readability and engagement. This gap arises mainly from the absence of suitable reward models to guide agentic workflows toward producing documents with stronger structural and stylistic quality. To address this, we propose DocReward, a document reward model that evaluates documents based on their structure and style. We construct a multi-domain dataset DocPair of 117K paired documents, covering 32 domains and 267 document types, each including a high- and low-professionalism document with identical content but different structure and style. This enables the model to evaluate professionalism comprehensively, and in a textual-quality-agnostic way. DocReward is trained using the Bradley-Terry loss to score documents, penalizing predictions that contradict the annotated ranking. To assess the performance of reward models, we create a test dataset containing document bundles ranked by well-educated human evaluators. Notably, DocReward outperforms GPT-4o and GPT-5 in accuracy by 30.6 and 19.4 percentage points, respectively, demonstrating its superiority over baselines. In an extrinsic evaluation of document generation, DocReward achieves a significantly higher win rate of 60.8%, compared to GPT-5's 37.7% win rate, demonstrating its utility in guiding generation agents toward producing human-preferred documents.

Community

Paper author Paper submitter

Introducing DocReward, a document reward model that evaluates documents based on their structure and style.

cool paper

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2510.11391 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2510.11391 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2510.11391 in a Space README.md to link it from this page.

Collections including this paper 2