标签还是输入？重新思考多模态仇恨检测中的增强
Labels or Input? Rethinking Augmentation in Multimodal Hate Detection
AI总结：
本文提出通过提示优化、微调和自动化数据增强改进小型模型，开发多模态增强框架以提升隐含仇恨检测性能。
摘要：
在线仇恨仍是一个重大的社会挑战，尤其是在多模态内容使微妙、文化相关和隐含形式的伤害成为可能的情况下。仇恨表情包通过文本-图像互动和幽默嵌入敌意，使自动系统难以解读。尽管最近的视觉-语言模型（VLMs）在显性案例上表现良好，但其部署受到高推理成本和持续失败于细微内容的限制。本文研究了通过提示优化、微调和自动化数据增强，小型模型能被改进到何种程度。我们介绍了一个端到端的流程，通过变化提示结构、标签粒度和训练模式，表明结构化提示和扩展监督显著增强了紧凑的VLMs。我们还开发了一种多模态增强框架，通过协调的LLM-VLM设置生成反事实中性的表情包，减少伪相关性并提高隐含仇恨的检测。消融研究量化了每个组件的贡献，证明提示设计、细粒度标签和针对性增强共同缩小了小型和大型模型之间的差距。结果提供了一条通往更稳健和可部署的多模态仇恨检测系统的方法，而无需依赖昂贵的大模型推理。
英文摘要：
Online hate remains a significant societal challenge, especially as multimodal content enables subtle, culturally grounded, and implicit forms of harm. Hateful memes embed hostility through text-image interactions and humor, making them difficult for automated systems to interpret. Although recent Vision-Language Models (VLMs) perform well on explicit cases, their deployment is limited by high inference costs and persistent failures on nuanced content. This work examines how far small models can be improved through prompt optimization, fine-tuning, and automated data augmentation. We introduce an end-to-end pipeline that varies prompt structure, label granularity, and training modality, showing that structured prompts and scaled supervision significantly strengthen compact VLMs. We also develop a multimodal augmentation framework that generates counterfactually neutral memes via a coordinated LLM-VLM setup, reducing spurious correlations and improving the detection of implicit hate. Ablation studies quantify the contribution of each component, demonstrating that prompt design, granular labels, and targeted augmentation collectively narrow the gap between small and large models. The results offer a practical path toward more robust and deployable multimodal hate-detection systems without relying on costly large-model inference.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
