跳到正文
arXiv · 机器人与计算机视觉· Zhivar Sourati, Marianne Menglin Liu, Rongguang Wang, Zheng Wang, Yazhe Hu, Lan Guo, Yuying Wang, Mengqing Guo, Bhavesh Dnyaneshwar Gore, Shubham Pathak, Ramapriya Ranganath, Sandeep Sharma, Tao Sheng, Sujith Ravi, Dan Roth·· 2026-10-16AI 评分72

VELD-QA:长文档中基于视觉证据定位与问答的大规模基准数据集

VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long Documents

AI 导读

VELD-QA 是一个针对长文档视觉证据定位与问答的大规模基准数据集,包含 5,859 个真实 PDF 文件共 372,445 页的 15,000 组人工标注问答对。

来源:arXiv · 机器人与计算机视觉 · arxiv.org