This paper introduces AMMORE, a new dataset of 53,000 math open-response question-answer pairs from Rori, a mathematics learning platform used by middle and high school students in several African countries. Using this dataset, we conducted two experiments to evaluate the use of large language models (LLM) for grading particularly challenging…

By participating in asynchronous course discussion forums, students can work together to refine their ideas and construct knowledge collaboratively. Typically, some messages simply repeat or paraphrase course content, while others bring in new material, demonstrate reasoning, integrate concepts, and develop solutions. Through the messages they…