Frontier-AI-Research/MORALISE
收藏Hugging Face2025-10-27 更新2025-11-01 收录
下载链接:
https://hf-mirror.com/datasets/Frontier-AI-Research/MORALISE
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是用于评估文本和图像中心设置的模型道德对齐的评估代码和数据集。它包括文本中心的正确和错误道德示例,图像中心的正确和错误道德示例,以及包含多标签信息的完整文本和图像数据集。
This dataset is for evaluating model moral alignment in text-centric and image-centric settings. It includes text-centric morally correct and wrong examples, image-centric morally correct and wrong examples, and complete datasets with multi-label annotations for text and image cases.
提供机构:
Frontier-AI-Research



