Multimodal Large Language Models Harmlessness Alignment Dataset
收藏DataCite Commons2026-01-07 更新2025-04-16 收录
下载链接：
https://service.tib.eu/ldmservice/dataset/23082431-6c24-4b89-a9f7-3fa0aa7847aa
下载链接
链接失效反馈官方服务：
资源简介：
The dataset used in the paper to evaluate the harmlessness alignment of multimodal large language models (MLLMs). The dataset consists of 750 harmful instructions paired with corresponding images.
提供机构：
TIB
创建时间：
2025-01-03
