openbmb/VisRAG-Ret-Test-ArxivQA

这是一个基于从arXiv论文中提取的图表构建的VQA数据集。它包含三个配置：语料库（包含图像及其标识符），qrels（包含查询相关性的判断），以及查询（包含与图像相关的问题、答案和选项）。数据集被划分为训练集，并提供了分割的大小、下载大小和数据集大小。该数据集基于Multimodal ArXiV论文中的ArXiVQA数据集。

This is a VQA dataset based on figures extracted from arXiv publications. It includes three configurations: corpus (containing images and their identifiers), qrels (containing query-relevance judgments), and queries (including questions, answers, and options related to the images). The dataset is split into a training set, and the sizes of the splits, as well as the download size and dataset size, are provided. The dataset is based on the ArXiVQA dataset from the Multimodal ArXiV paper.