Mindgames

该数据集包含了400个问题，旨在评估语言模型中的心智理论（Theory of Mind）。这些问题的真/假标签分布均衡，非常适合进行零样本和少样本实验，以测试不同语言模型的能力。This dataset contains 400 questions designed to evaluate the Theory of Mind (ToM) in language models. The true/false labels of these questions are evenly distributed, making it highly suitable for zero-shot and few-shot experiments to test the capabilities of various language models.