研究人员推出了新的基准和改进的模型，用于文档解析和表格提取。Dr. DocBench 专注于专家级别的文档解析，包括化学式和音乐符号等复杂结构，突出了当前模型的局限性。DTBench 提供了一个用于文档到表格提取的合成基准，评估 LLM 的推理和冲突解决能力。此外，PaddleOCR-VL-1.6 通过区域感知优化和渐进式后训练得到了增强，在 OmniDocBench v1.6 上取得了最先进的结果。 AI
影响 文档和表格提取基准和模型的进步将提高 AI 处理和分析复杂文档和数据的能力。
排序理由 多篇研究论文介绍了用于文档解析和表格提取的新基准和模型改进。
AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →
arXiv:2606.01393v1 Announce Type: cross Abstract: Document parsing and recognition are fundamental capabilities for vision-language models (VLMs) and document processing systems. However, existing Optical Character Recognition (OCR) and document parsing benchmarks are increasingl…
arXiv:2603.18652v2 Announce Type: replace-cross Abstract: Reliably extracting tables from PDFs is essential for large-scale scientific data mining and knowledge base construction, yet existing evaluation approaches rely on rule-based metrics that fail to capture semantic equivale…
PaddleOCR-VL-1.6 enhances document parsing performance through targeted data optimization and progressive post-training techniques, achieving state-of-the-art results on OmniDocBench v1.6.
arXiv:2602.13812v3 Announce Type: replace-cross Abstract: Document-to-table (Doc2Table) extraction derives structured tables from unstructured documents under a target schema, enabling reliable and verifiable SQL-based data analytics. Although large language models (LLMs) have sh…
arXiv:2606.03264v1 Announce Type: new Abstract: We introduce PaddleOCR-VL-1.6, an upgraded compact document parsing model built upon PaddleOCR-VL-1.5. Although PaddleOCR-VL-1.5 establishes a strong 0.9B baseline, its remaining errors concentrate in under-optimized regions where m…
arXiv:2512.10888v3 Announce Type: replace Abstract: Table extraction (TE) is a key challenge in document understanding. Traditional approaches detect tables first, then recognize their structure. Recently, interest has surged in developing methods, such as vision-language models …