专为金融文档设计的结构化解析系统，支持跨页连续性与细粒度单元定位。
LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Reference
- 融合跨页内容整合与全局目录重建，实现文档级结构一致性
- 在FinDocBench上表单元交并比达0.82，跨页文本编辑距离相似度超0.91
- 适合金融审计、合规等对精度和可追溯性要求高的场景
本文提出LingDT-VL-OCR，一个面向金融领域文档的解析系统，能将超长金融PDF转化为语义一致、高精度的结构化输出，并具备审计级溯源能力。针对金融文档复杂版式、跨页结构断裂及单元级引用等挑战，系统结合跨页内容整合算法与文档级标题层级重建（DHR）模块，构建全局一致的目录树以支持结构化检索；同时采用难度自适应课程学习策略训练表格解析模型，并引入CellBBoxRegressor模块，利用结构锚点令牌从解码器隐藏状态直接定位表格单元，无需外部检测器。实验表明，该模型在OmniDocBench总体指标上表现优异。为进一步评估金融垂直领域的实际性能，我们构建了FinDocBench基准，包含六类金融文档，具有专家标注与多项评价指标：基于目录编辑距离的相似度（TocEDS）、跨页拼接的文本编辑距离相似度（TEDS）以及表单元交并比（C-IoU）。我们在该基准上评估多种前沿模型，揭示其在金融文档上的能力边界。整体而言，LingDT-VL-OCR与FinDocBench为金融文档的可靠下游应用提供了实践基础。
原文摘要 · Abstract (English)
In this paper, we propose LingDT-VL-OCR, a document parsing system tailored to financial-domain documents, transforming ultra-long financial PDFs into semantically consistent, highly accurate, structured outputs with auditing-grade provenance. To address finance-specific challenges such as complex layouts, cross-page structural discontinuities, and cell-level referencing capability, LingDT-VL-OCR combines (1) a Cross-page Contents Consolidation algorithm to restore continuity across pages and a Document-level Heading Hierarchy Reconstruction (DHR) module to build a globally consistent Table of Contents (TOC) tree for structure-aware retrieval, and (2) a difficulty-adaptive curriculum learning training strategy for table parsing, together with a CellBBoxRegressor module that uses structural anchor tokens to localize table cells from decoder hidden states without external detectors. Experiments demonstrate that our model shows high performance on the Overall metric of OmniDocBench. To enable realistic evaluation in the financial vertical, we further introduce FinDocBench, a benchmark that includes six financial document categories with expert-verified annotations and evaluation metrics including Table of Contents edit-distance-based similarity (TocEDS), cross-page concatenated TEDS, and Table Cell Intersection over Union (C-IoU). We evaluate a wide range of state-of-the-art models on FinDocBench to assess their capabilities and remaining limitations on financial documents. Overall, LingDT-VL-OCR and FinDocBench provide a practical foundation for reliable downstream financial document applications.
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。