Multimodal Large Language Models Harmlessness Alignment Dataset

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.

Data and Resources

Cite this as

Yifan Li, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Ji-Rong Wen (2025). Dataset: Multimodal Large Language Models Harmlessness Alignment Dataset. https://doi.org/10.57702/xkga8cje

DOI retrieved: January 3, 2025

Additional Info

Field Value
Created January 3, 2025
Last update January 3, 2025
Defined In https://doi.org/10.48550/arXiv.2403.09792
Author Yifan Li
More Authors
Hangyu Guo
Kun Zhou
Wayne Xin Zhao
Ji-Rong Wen
Homepage https://github.com/RUCAIBox/HADES