CHATS-Lab/Verbalized-Sampling-Random-Number-Generator

Verbalized-Sampling-Random-Number-Generator数据集用于评估Verbalized Sampling (VS)在生成均匀随机分布方面的有效性。该数据集包括来自各种最先进的LLM在简单随机生成任务上的响应。数据集的结构包括不同的配置，代表不同的提示方法，以及不同的分割，代表不同的语言模型。README还包含了关于数据集结构、数据字段、资源、用法、统计、创建、偏差、局限性、许可证、引用和联系信息。

The Verbalized-Sampling-Random-Number-Generator dataset evaluates the effectiveness of Verbalized Sampling (VS) in generating uniform random distributions. It includes responses from various state-of-the-art LLMs on simple random generation tasks. The dataset is structured into different configurations representing different prompting methods and splits representing different language models. The README also includes information about the dataset structure, data fields, resources, usage, statistics, creation, biases, limitations, license, citation, and contact information.