Crisp-Unimib/BEEP_eval
收藏官方服务：
资源简介：
BEEP（最佳驾驶执照表现者）数据集是一个挑战性基准，旨在通过模拟意大利驾驶执照考试来评估大型语言模型（LLM）。该数据集专注于理解交通法规和驾驶情况下的推理，复制意大利执照流程的复杂性。
BEEP (BEst DrivEr’s License Performer) Dataset is a challenge benchmark designed to evaluate large language models (LLMs) through a simulation of the Italian driver’s license exam. This dataset focuses on understanding traffic laws and reasoning through driving situations, replicating the complexity of the Italian licensing process.
提供机构：
Crisp-Unimib
