nbalepur/planorama_without_label

这是一个包含数学和Trivia问题的数据集，每个问题都有对应的答案和生成模型。数据集中的字段包括问题ID、类别、问题内容、答案、生成模型、两种不同的计划（plan_a和plan_b）、模型比较、两种模型的准确性、两种模型的时间消耗、人类比较结果、人类比较ID、两种模型在人类判断中的准确性、时间消耗、是否见过所有问题、是否见过某个类别的问题以及人类ID等信息。数据集分为数学和Trivia两个部分，每个部分包含150个示例。

This dataset contains math and trivia questions, each with corresponding answers and generation models. The fields in the dataset include question ID, category, question content, answer, generation model, two different plans (plan_a and plan_b), model comparison, accuracy of two models, time consumption of two models, human comparison results, human comparison IDs, accuracy of two models in human judgments, time consumption, whether all questions have been seen, whether questions of a certain category have been seen, and human IDs, etc. The dataset is divided into math and trivia sections, each containing 150 examples.