TimeBench
收藏arXiv2025-09-30 收录
下载链接：
https://github.com/zchuz/TimeBench
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是一个全面的多层次时间推理基准，涵盖了广泛的时间推理现象。TimeBench旨在评估大型语言模型的时间推理能力，并突出其与人类能力之间的性能差距。该任务旨在对大型语言模型进行时间推理能力的评估。
This dataset, named TimeBench, is a comprehensive multi-level temporal reasoning benchmark that covers a wide range of temporal reasoning phenomena. It aims to evaluate the temporal reasoning capabilities of large language models and highlight the performance gap between these models and human abilities. This task is designed to evaluate the temporal reasoning capabilities of large language models.
提供机构：
Authors of the paper
