UCSD-GENIE/ClimaQA

ClimaQA是一个针对气候科学问题回答任务的自动评估框架，旨在确保科学严谨性和复杂性。它由研究生级别的气候科学教科书构建，提供了一个可靠的基础，用于生成具有精确术语和复杂科学理论的问题。该基准包含两个数据集：ClimaQA-Gold（经过专家验证的数据集）和ClimaQA-Silver（大规模合成数据集）。

ClimaQA is an automated evaluation framework designed for climate science question-answering tasks, ensuring scientific rigor and complexity. It is built from graduate-level climate science textbooks, providing a reliable foundation for generating questions with precise terminology and complex scientific theories. The benchmark consists of two datasets: ClimaQA-Gold (an expert-validated dataset) and ClimaQA-Silver (a large-scale synthetic dataset).