LogicPrpBank

该数据集名为LogicPrpBank，专为进行命题逻辑正确性分类的基准实验而构建。该数据集被划分为训练集（70%）、验证集（10%）和测试集（20%），用于评估不同语言模型的性能。这些语言模型的规模属于小型和中型，所承担的任务是命题逻辑正确性（真/假）分类。

This dataset, named LogicPrpBank, is constructed specifically for benchmark experiments on propositional logic correctness classification. It is divided into three subsets: the training set (70%), validation set (10%), and test set (20%), which are used to evaluate the performance of small and medium-sized language models. The task assigned to these models is propositional logic correctness (true/false) classification.