牛津大学与Rising Academies加纳学生阅读理解简答题数据集

牛津大学与Rising Academies合作创建了加纳学生阅读理解简答题数据集，包含来自加纳130名学生的超过1500个阅读理解问题的答案。该数据集旨在评估大型语言模型在不同文化背景下的表现，并促进对低收入和中等收入国家学生教育需求的理解。数据集内容包括学生的原始测试、阅读理解问题的答案以及专家评分员的评分。该数据集的应用领域主要集中在教育评估，特别是阅读理解的形成性评估，旨在通过自动化评分提高评估效率和准确性。

University of Oxford and Rising Academies collaborated to create a dataset of short-answer reading comprehension questions for Ghanaian students, which contains over 1,500 responses to reading comprehension tasks from 130 Ghanaian students. This dataset is designed to evaluate the performance of large language models (LLMs) across diverse cultural contexts, and foster a better understanding of the educational needs of students in low- and middle-income countries. The dataset includes students' original test submissions, their responses to the reading comprehension questions, and scores assigned by expert raters. Its primary application domains focus on educational assessment, particularly formative reading comprehension assessment, with the goal of improving assessment efficiency and accuracy via automated scoring.