研究人员开发了一种提示式弱监督（PWS）方法，以改进表情包中的仇恨言论检测，解决了其多模态性质和微妙文化线索带来的挑战。该方法将表情包理解分解为有针对性的、基于问题的标注函数，优于视觉-语言模型的直接分类。PWS方法在多语言环境中显示出显著的提升，尤其是在中文和印地语方面，在LT-EDI 2026共享任务中获得最高排名。 AI
影响 引入了一种新颖的多模态仇恨言论检测方法，有望改善在线内容审核的安全措施。
排序理由 该集群包含一篇详细介绍特定AI任务新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.24179v1 Announce Type: new Abstract: Detecting hate speech in memes is challenging due to their multimodal nature and subtle, culturally grounded cues such as sarcasm and context. While recent vision-language models (VLMs) enable joint reasoning over text and images, e…
Detecting hate speech in memes is challenging due to their multimodal nature and subtle, culturally grounded cues such as sarcasm and context. While recent vision-language models (VLMs) enable joint reasoning over text and images, end-to-end prompting can be brittle, as a single …