OpenDFM/AirQA
收藏Hugging Face2026-02-17 更新2026-02-07 收录
下载链接：
https://hf-mirror.com/datasets/OpenDFM/AirQA
下载链接
链接失效反馈官方服务：
资源简介：
AirQA是一个人工标注的多模态多任务人工智能研究问答数据集，包含1,246个示例和13,956篇论文，旨在评估代理在现实场景中的研究能力。它是第一个涵盖多种问题类型的数据集，也是第一个将基于功能的评估引入问答领域的数据集，便于系统和便捷地评估研究能力。数据集涵盖了34卷论文，跨越7个会议和16年时间。
AirQA is a human-annotated multi-modal multitask Artificial Intelligence Research Question Answering dataset, which encompasses 1,246 examples and 13,956 papers, aiming at evaluating an agent’s research capabilities in realistic scenarios. It is the first dataset that encompasses multiple question types, also the first to bring function-based evaluation into QA domain, enabling convenient and systematic assessment of research capabilities. The dataset encompasses papers from 34 volumes, spanning 7 conferences over 16 years.
提供机构：
OpenDFM
