SamsungSDS-Research/SDS-KoPub-VDR-Benchmark

SDS KoPub-VDR是一个针对韩国公共文档的视觉文档检索任务的数据集，包含真实世界的政府文档图像和与自然语言查询相对应的答案页面以及地面真实答案。该数据集旨在评估AI模型在理解视觉布局、表格、图表和图像以进行准确的文档级视觉理解和检索方面的能力。

SDS KoPub-VDR is a benchmark dataset for Visual Document Retrieval (VDR) in the context of Korean public documents, containing real-world government document images paired with natural-language queries, corresponding answer pages, and ground-truth answers. The dataset is designed to evaluate AI models capability of comprehensive document-level visual understanding and retrieval by comprehending visual layouts, tables, graphs, and images.