yale-nlp/Bright-Pro

Bright-Pro是一个专家标注的扩展版BRIGHT基准，专注于推理密集型检索。数据集包含7个StackExchange领域的739个查询，每个查询都配有多方面的推理分解、重要性权重分数以及按方面组织的精选黄金段落。数据集旨在支持细粒度分析，评估检索器是否能覆盖回答查询所需的互补推理方面，而不仅仅是找到一个相关段落。数据集包含三个配置：examples（查询级注释）、aspects（推理方面注释）和documents（语料库）。此外，数据集还提供了详细的统计信息、快速开始指南、评估方法以及与原BRIGHT数据集的区别。Bright-Pro is an expert-annotated extension of the BRIGHT benchmark for reasoning-intensive retrieval. Each query is paired with a multi-aspect reasoning decomposition, weighted importance scores per aspect, and a curated set of gold passages organized by aspect — enabling fine-grained analysis of whether a retriever covers the complementary reasoning aspects required to answer a query, rather than just surfacing one relevant passage. The dataset includes three configurations: examples (query-level annotations), aspects (reasoning-aspect annotations), and documents (corpus). Additionally, the dataset provides detailed statistics, a quick start guide, evaluation methods, and differences from the original BRIGHT dataset.