Model Releases
When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models
arXiv:2610.22068v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can act unsafely when individually benign images and texts are interpreted jointly. Beyond implicit reasoning r
arXiv:2610.22068v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can act unsafely when individually benign images and texts are interpreted jointly. Beyond implicit reasoning risk, where reasoning drifts toward harm, we identify intent-level risk, where cross-modal ambiguity silently commits the model to a hazardous premise that path-level optimization alone cannot correct. We propose SAFE-PRO, which uses a Risk-Conditioned Uncertainty (RCU) signal, combining predictive entropy with a learned cross-modal risk score, to decide when to ask safety-grounded clarifying questions and where to apply path optimization, under a reward that prioritizes safety and penalizes over-refusal. We also build SSUI-Dialog, a multimodal multi-turn dataset with dual-intent supervision, and theoretically analyze gradient variance and unsafe-completion risk under RCU. Across seven benchmarks and two base MLLMs, SAFE-PRO consistently improves safety over SRPO, roughly halves its over-refusal, and surpasses GPT-4o and Claude-3.5-Sonnet in average single-turn safety.
Related
- CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
- Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
- Anchoring Bias: A Persistent Fairness Backdoor Attack against MLLMs under Continual Learning
- SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs
Source: arXiv cs.AI | 2026-10-16