RobustQA

该数据集名为RobustQA，是一个大规模的开放式问答评估基准，旨在评估开放式问答模型在跨领域泛化能力方面的表现。它包含了来自FiQA、SearchQA、BioASQ和LOTTE等来源的问答对及相应文档。该数据集的任务是开放域问答。The dataset is named RobustQA, a large-scale open-ended question answering evaluation benchmark designed to assess the cross-domain generalization capability of open-ended question answering models. It includes question-answer pairs and their corresponding documents sourced from FiQA, SearchQA, BioASQ, LOTTE and other related resources. The task of this dataset is open-domain question answering.