arXiv cs.AI· Wei Cai, Jian Zhao, Yuchen Yuan, Xuelong Li·· 2 天前AI 评分31
SAFE-PRO：用主动提问解决多模态大模型的跨模态安全风险
When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models
AI 导读
针对多模态大模型在图文联合解读时出现的意图级风险，研究者提出 SAFE-PRO，利用结合预测熵与跨模态风险分数的 Risk-Conditioned Uncertainty（RCU）信号，判断何时提出安全澄清问题、何处应用路径优化。
正文 · 原文
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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.22068 [cs.AI] |
| (or arXiv:2610.22068v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22068 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wei Cai [view email]
[v1]
Thu, 15 Oct 2026 15:28:47 UTC (5,152 KB)
来源：arXiv cs.AI · arxiv.org