多视角智能体辩论框架提升社交平台有害内容识别准确率
MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media
- 构建四类智能体从不同角度分析图文混合内容
- 迭代辩论与动态反思机制使准确率显著提升
- 适合关注社交媒体安全与多模态内容检测的研究者
社交媒体已演变为复杂的多模态环境，文本、图像等信号相互交织，常隐含有害意图。识别讽刺、仇恨言论或虚假信息等行为，因跨模态矛盾、文化快速变化及微妙语用线索而极具挑战。为此，本文提出MV-Debate，一种基于动态反思门控的多视图智能体辩论框架，用于统一的多模态有害内容检测。该框架集成四类互补智能体：表面分析者、深层推理者、模态对比者与社会语境分析师，从多元视角解析内容。通过迭代辩论与反思，在反射增益准则下优化输出，兼顾准确性与效率。在三个基准数据集上的实验表明，MV-Debate显著优于强基线单模型及现有多智能体辩论方法。本工作凸显了多智能体辩论在安全关键在线场景中提升社交意图识别可靠性的潜力。
原文摘要 · Abstract (English)
Social media has evolved into a complex multimodal environment where text, images, and other signals interact to shape nuanced meanings, often concealing harmful intent. Identifying such intent, whether sarcasm, hate speech, or misinformation, remains challenging due to cross-modal contradictions, rapid cultural shifts, and subtle pragmatic cues. To address these challenges, we propose MV-Debate, a multi-view agent debate framework with dynamic reflection gating for unified multimodal harmful content detection. MV-Debate assembles four complementary debate agents, a surface analyst, a deep reasoner, a modality contrast, and a social contextualist, to analyze content from diverse interpretive perspectives. Through iterative debate and reflection, the agents refine responses under a reflection-gain criterion, ensuring both accuracy and efficiency. Experiments on three benchmark datasets demonstrate that MV-Debate significantly outperforms strong single-model and existing multi-agent debate baselines. This work highlights the promise of multi-agent debate in advancing reliable social intent detection in safety-critical online contexts.
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。