Shirinap123/Belief-and-Biases-Bench
收藏官方服务：
资源简介：
Belief and Biases Bench是一个全面的合成数据集，旨在评估大型语言模型在准确识别人类对话中的信念和认知偏见方面的能力。该数据集提供了丰富的会话交互集合，其中展示了各种认知偏见以及通过策略性推动技术来应对这些偏见的过程。
The Belief and Biases Bench is a comprehensive synthetic dataset designed to evaluate the capability of Large Language Models (LLMs) in accurately identifying beliefs and cognitive biases in human conversations. This dataset provides a rich collection of conversational interactions where various cognitive biases are exhibited and addressed through strategic nudging techniques.
提供机构：
Shirinap123
