bench-temp/mmlu-pt-undergraduate-ablation-v2-notink-unbalanced
收藏数据链接：
官方服务：
资源简介：
该数据集是一个多学科的问题回答数据集，包含会计、建筑、工商管理、经济学、健康与生物科学、人文学科、语言、法律和STEM等9个学科领域的题目。每个样本包含原始任务文本、问题ID、正确回答的难度计数和难度分数，可用于评估模型在不同学科上的问答能力。
This dataset is a multi-disciplinary question-answering dataset covering 9 subject areas: accounting, architecture, business administration, economics, health and biological sciences, humanities, languages, law, and STEM. Each sample includes the raw task text, question ID, difficulty count of correct answers, and difficulty score, which can be used to evaluate model performance on question answering across different disciplines.
提供机构：
bench-temp
