通过分步纠错提升文档解析准确率，重点修复关键错误。
ParseFixer: An Agentic Framework for Document Parsing via Selective Multimodal Correction
- 先用基础模型生成初步结构，再智能识别并修正关键错误。
- 在测试集上取得61.78分，排名第三，显著提升关键元素恢复率。
- 适合需要高精度文档结构还原的场景，如自动化信息提取。
本文介绍我们在DataMFM挑战赛第1赛道的第三名解决方案——ParseFixer。该赛道要求从页面图像中恢复出结构化的Markdown文档，同时保持文本内容和文档结构的准确性。为兼顾内容恢复的精确性与结构重建的忠实度，我们提出一种代理式框架，包含两个核心模块：全页骨干解析（FBP）和代理选择性修正（ASC）。FBP基于MinerU2.5 Pro生成稳定初始的Markdown输出；ASC则通过验证与回滚机制，检测并修复高价值的解析失败。该方法在开源骨干模型基础上进行选择性多模态修正，避免重写可靠的预测结果。最终系统在测试集上获得61.78分，位列第3，证明了其在精准文档解析中的有效性。代码将公开于https://github.com/iLearn-Lab/CVPRW26-ParseFixer。
原文摘要 · Abstract (English)
In this report, we present our third-place solution for the DataMFM Challenge Track 1: Document Parsing. This track requires models to recover structured Markdown documents from document page images while preserving textual content and document structure. To address the complementary requirements of accurate content recovery and faithful structure reconstruction, we propose ParseFixer, an agentic framework for backbone parsing and selective correction. ParseFixer consists of two key modules: Full-Page Backbone Parsing (FBP) and Agentic Selective Correction (ASC). FBP produces stable initial Markdown outputs with MinerU2.5 Pro, while ASC detects high-value parsing failures and repairs them through a verify-and-rollback correction process. By placing selective multimodal correction after open-source backbone parsing, ParseFixer improves the recovery of key document elements without rewriting reliable backbone predictions. On the test set, our final system achieves an overall score of 61.78 and ranks third in Track 1, demonstrating its effectiveness for accurate document parsing. Our code will be released at: https://github.com/iLearn-Lab/CVPRW26-ParseFixer.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。