SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

• URL: http://arxiv.org/abs/2606.22873v3
• Date: Thu, 25 Jun 2026 18:44:01 GMT
• Title: SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
• Abstract summary: We present textbfSingGuard, a policy-adaptive guardrail model family for safety assessment in multimodal conversations.<n>SingGuard treats the active policy as a runtime input.<n>It checks the target content against the active policy rule by rule and predicts both the safety label and the triggered rule.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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 \textbf{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 \textbf{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.

Related papers

• ActSafeGuard: Differentiable and Training-Aligned Constraint Enforcement for Flow-Matching Policies [13.296422778046148]
  We introduce ActSafeGuard, a differentiable and training-aligned safeguard layer for flow-matching based policies.<n>ActSafeGuard integrates hard action feasibility into policy learning, not merely treating safety as an inference-time external component.
  arXiv  Detail & Related papers  (2026-09-10T15:21:47Z)
• EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents [74.54929751174289]
  EvoSafeHarness is a safety-specific optimization framework that synthesizes a deployable harness for a frozen model in a target domain.<n>It reduces average attack success rate from 45.6% to 10.0% at a 3.3-point utility cost.<n>It also achieves the best score on Agent-SafetyBench for every victim.
  arXiv  Detail & Related papers  (2026-09-05T05:56:41Z)
• Harnessing Textual Refusal Directions for Multimodal Safety [70.16764304975675]
  We introduce Modality-Agnostic Refusal Steering (MARS), a light-weight training-free approach that injects multimodal safety without the need for multimodal safety data.<n>MARS corrects modality misalignment via activation re-centering, adaptively scales steering strength within a geometrically defined trust region, and selects the optimal intervention layer.
  arXiv  Detail & Related papers  (2026-06-30T15:57:50Z)
• LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails [41.04710068888387]
  We introduce Latent Policy Guardrail (LPG), a guardrail framework that learnssemantic latent deliberation over dynamic policies.<n>Across policy guardrail benchmarks, LPG-4B reaches 84.5% average safety accuracy and 77.9% F1 by compressing deliberation into just 10 latent tokens.
  arXiv  Detail & Related papers  (2026-05-17T08:35:38Z)
• Selective Safety Steering via Value-Filtered Decoding [54.87935112120107]
  Large language models (LLMs) are trained to align with human values, but their generations may still violate safety constraints.<n>Existing decoding-time steering methods often intervene unnecessarily, modifying generations that would have been safe under the base model.<n>We propose a new test-time steering method designed to reduce such unnecessary interventions while improving the safety of unsafe responses.
  arXiv  Detail & Related papers  (2026-05-14T12:13:08Z)
• ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving [63.980630608984605]
  This paper presents ADV-0, a closed-loop min-max optimization framework that treats the interaction between driving policy (defender) and adversarial agent (attacker) as a zero-sum Markov game.<n>To make this tractable, we cast dynamic adversary evolution as iterative preference learning, efficiently approximating this optimum and offering an algorithm-agnostic solution to the game.<n> Experiments indicate that it effectively exposes diverse safety-critical failures and greatly enhances the generalizability of both learned policies and motion planners against unseen long-tail risks.
  arXiv  Detail & Related papers  (2026-03-16T12:58:31Z)
• Towards Policy-Adaptive Image Guardrail: Benchmark and Method [21.041111216560545]
  Vision-language models (VLMs) offer a more adaptable and generalizable foundation for dynamic safety guardrails.<n>Existing VLM-based safeguarding methods are typically trained and evaluated under only a fixed safety policy.<n>We introduce SafeGuard-VL, a reinforcement learning-based method with verifiable rewards for robust unsafe-image guardrails.
  arXiv  Detail & Related papers  (2026-03-01T18:59:21Z)
• SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization [79.14563283347773]
  Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities.<n>Cross-modal couplings can produce unsafe semantics even when individual inputs are benign.<n>We propose SafeGRPO, a self-rewarded multimodal safety alignment framework.
  arXiv  Detail & Related papers  (2025-11-17T05:09:49Z)
• Qwen3Guard Technical Report [127.69960525219051]
  We present Qwen3Guard, a series of multilingual safety guardrail models with two specialized variants.<n>Generative Qwen3Guard casts safety classification as an instruction-following task to enable fine-grained tri-class judgments.<n>Stream Qwen3Guard introduces a token-level classification head for real-time safety monitoring.
  arXiv  Detail & Related papers  (2025-10-16T04:00:18Z)
• COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability [101.80200069234377]
  We present COSMO-RL, a mixed reinforcement learning framework that trains LMRMs under multimodal, multitask, and multiobjective signals.<n>Our approach aims to let safety and capability grow together in one stable pipeline rather than competing during alignment.
  arXiv  Detail & Related papers  (2025-10-05T13:30:03Z)
• Automating Steering for Safe Multimodal Large Language Models [58.36932318051907]
  We introduce a modular and adaptive inference-time intervention technology, AutoSteer, without requiring any fine-tuning of the underlying model.<n>AutoSteer incorporates three core components: (1) a novel Safety Awareness Score (SAS) that automatically identifies the most safety-relevant distinctions among the model's internal layers; (2) an adaptive safety prober trained to estimate the likelihood of toxic outputs from intermediate representations; and (3) a lightweight Refusal Head that selectively intervenes to modulate generation when safety risks are detected.
  arXiv  Detail & Related papers  (2025-07-17T16:04:55Z)
• GuardSet-X: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset [18.306944278068638]
  We introduce GuardSet-X, the first massive multi-domain safety policy-grounded guardrail dataset.<n> GuardSet-X offers broad domain coverage across eight safety-critical domains, such as finance, law, and codeGen.<n>We benchmark 19 advanced guardrail models and uncover a series of findings.
  arXiv  Detail & Related papers  (2025-06-18T01:35:33Z)
• SAGE: A Generic Framework for LLM Safety Evaluation [7.5058318880108885]
  We introduce SAGE (Safety AI Generic Evaluation), an automated modular framework for customized and dynamic harm evaluations.<n>We evaluate seven state-of-the-art Large Language Models across three applications and harm policies.<n>Results motivate adaptive, policy-aware, and context-specific testing for safer real-world deployment.
  arXiv  Detail & Related papers  (2025-04-28T11:01:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.