SingGuard：一种具有动态推理能力的、能适应政策的多模态LLM监管框架
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
摘要
视觉-语言模型在消费者、医疗、金融和企业领域得到了越来越多的应用。这种广泛的应用范围扩大了安全保障的范围：多模态问答、助手回复以及跨模态组合行为都可能带来风险，而管理策略则可能因产品、地区和部署阶段的不同而有所差异。目前大多数安全约束机制要么依赖固定的分类体系，要么只针对有限的互动方式，这导致当安全规则发生变化时，这些机制无法适应变化。我们提出了SingGuard——一种能够适应不同场景的多模态安全评估模型。SingGuard将主动策略视为运行时输入：根据自然语言规则，它逐条检查目标内容是否符合相关策略，同时预测出安全标签以及被触发的策略。为了平衡效率与可解释性，SingGuard支持快速、混合和慢速推理模式，从直接的安全判断到基于策略的详细分析都有涵盖。我们通过快速-慢速分离强化学习技术进一步优化了这种行为。此外，我们还引入了SingGuard-Bench这一多模态安全评估基准，该基准包含56,340个样本，涵盖了80多种细微的风险类型，涉及多模态问答、对抗性攻击和动态规则评估场景，包括那些各模态单独来看并无问题，但组合后却存在安全隐患的情况。在六个基准数据集上，SingGuard在每个基准中都取得了最先进的F1分数。动态规则评估还表明，在策略变化的情况下，其遵循策略的准确性从0.6465提升到了0.7415。我们的代码可以在https://github.com/inclusionAI/Sing-Guard上获取。
English Abstract
Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface: risks can arise from multimodal question answering, assistant responses, and cross-modal composition, while moderation policies may vary across products, regions, and deployment stages. Most existing guardrails either rely on fixed taxonomies or target only a narrow set of interaction settings, which limits their adaptability when safety rules change at deployment time. We present SingGuard, a policy-adaptive multimodal guardrail model family for safety assessment in multimodal conversations. SingGuard treats the active policy as a runtime input: given natural-language rules, it checks the target content against the active policy rule by rule and predicts both the safety label and the triggered rule. To balance efficiency and interpretability, SingGuard supports fast, hybrid, and slow inference regimes along a fast-to-slow reasoning spectrum, ranging from direct safety judgments to policy-grounded deliberation. We further optimize this behavior with fast--slow decoupled reinforcement learning. We also introduce SingGuard-Bench, a multimodal guardrail benchmark with 56{,}340 examples spanning 80+ fine-grained risk types across multimodal QA, adversarial attack, and dynamic-rule evaluation settings, including cross-modal joint-risk cases where each modality is harmless in isolation but their composition implies unsafe intent. Across six benchmark families (35 datasets), SingGuard achieves state-of-the-art average F1 in every family. Dynamic-rule evaluation further shows improved policy-following accuracy from 0.6465 to 0.7415 under runtime policy shifts. Our code is available at https://github.com/inclusionAI/Sing-Guard.