通过跨梗图关系推理，提升性别歧视内容检测效果
MEMEWEAVER: Inter-Meme Graph Reasoning for Sexism and Misogyny Detection
- 构建跨梗图图结构，捕捉网络仇恨内容的社交关联
- 在MAMI和EXIST数据集上优于现有方法，收敛更快
- 适合研究网络仇恨传播与多模态内容安全的学者
女性遭受在线骚扰的概率是男性的两倍。尽管多模态内容审核已有进展，但多数方法仍忽视背后的社会动态——施害者在志同道合的社群中强化偏见与群体认同。图模型可捕捉此类互动，但现有方法受限于启发式图构建、浅层模态融合及个体层面推理。本文提出MemeWeaver，一个端到端可训练的多模态框架，通过创新的跨梗图图推理机制检测性别歧视与厌女内容。我们系统评估多种视觉-文本融合策略，结果表明该方法在MAMI和EXIST基准上持续优于当前最优基线，且训练收敛更快。进一步分析显示，学习到的图结构捕获了语义上有意义的模式，揭示了网络仇恨的关联本质。
原文摘要 · Abstract (English)
Women are twice as likely as men to face online harassment due to their gender. Despite recent advances in multimodal content moderation, most approaches still overlook the social dynamics behind this phenomenon, where perpetrators reinforce prejudices and group identity within like-minded communities. Graph-based methods offer a promising way to capture such interactions, yet existing solutions remain limited by heuristic graph construction, shallow modality fusion, and instance-level reasoning. In this work, we present MemeWeaver, an end-to-end trainable multimodal framework for detecting sexism and misogyny through a novel inter-meme graph reasoning mechanism. We systematically evaluate multiple visual--textual fusion strategies and show that our approach consistently outperforms state-of-the-art baselines on the MAMI and EXIST benchmarks, while achieving faster training convergence. Further analyses reveal that the learned graph structure captures semantically meaningful patterns, offering valuable insights into the relational nature of online hate.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。