TrustAIRLab/Hateful_Memes_in_VLM
收藏Hugging Face2025-01-28 更新2025-02-15 收录
下载链接：
https://hf-mirror.com/datasets/TrustAIRLab/Hateful_Memes_in_VLM
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了不同视觉语言模型（InstructBlip、ShareGPT4V、LLaVA和CogVLM）对仇恨性表情的响应以及对这些响应的注释。更多信息请参考论文《From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language Models》。
This dataset contains the response of VLMs (InstructBlip, ShareGPT4V, LLaVA and CogVLM) to hateful memes and the annotation to these responses. For more information, please refer to paper From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language Models.
提供机构：
TrustAIRLab
