Test Collection with Utility Labels

该数据集是为了评估检索增强生成系统中的公平性而构建的测试集合，其中包含了针对各个项目级别的效用标签。这些项目级别的效用标签旨在与任务和生成器相关，反映了为语言模型提供的效用增益。该数据集的任务是评估检索增强生成系统中的公平性和排名质量。This dataset is a test collection developed to assess fairness in retrieval-augmented generation (RAG) systems, which includes project-level utility labels. These project-level utility labels are designed to be task- and generator-relevant, reflecting the utility gains provided to language models. The core task of this dataset is to evaluate the fairness and ranking quality of retrieval-augmented generation systems.