Short-video platforms now host vast multimodal ads whose deceptive visuals, speech and subtitles demand finer-grained, policy-driven moderation than community safety filters. We present BLM-Guard, a content-audit framework for commercial ads that fuses Chain-of-Thought reasoning with rule-based policy principles and a critic-guided reward. A rule-driven ICoT data-synthesis pipeline jump-starts training by generating structured scene descriptions, reasoning chains and labels, cutting annotation costs. Reinforcement learning then refines the model using a composite reward balancing causal coherence with policy adherence. A multitask architecture models intra-modal manipulations (e.g., exaggerated imagery) and cross-modal mismatches (e.g., subtitle-speech drift), boosting robustness. Experiments on real short-video ads show BLM-Guard surpasses strong baselines in accuracy, consistency and generalization.

翻译：短视频平台当前承载着海量多模态广告，其欺骗性视觉内容、语音及字幕需要比社区安全过滤器更细粒度、策略驱动的审核机制。本文提出BLM-Guard——面向商业广告的内容审核框架，该框架融合思维链推理、基于规则的策略原则与评论家引导的奖励机制。通过规则驱动的ICoT数据合成流程生成结构化场景描述、推理链与标注，显著降低标注成本并快速启动训练。强化学习随后采用平衡因果连贯性与策略遵从性的复合奖励对模型进行微调。多任务架构同时建模模态内操纵（如夸张图像）与跨模态失配（如字幕-语音偏移），从而增强系统鲁棒性。在真实短视频广告数据集上的实验表明，BLM-Guard在准确性、一致性和泛化能力方面均超越现有基线模型。