Score: 1

Safe Semantics, Unsafe Interpretations: Tackling Implicit Reasoning Safety in Large Vision-Language Models

Published: August 12, 2025 | arXiv ID: 2508.08926v1

By: Wei Cai , Jian Zhao , Yuchu Jiang and more

Potential Business Impact:

Fixes AI that makes bad choices from mixed pictures and words.

Large Vision-Language Models face growing safety challenges with multimodal inputs. This paper introduces the concept of Implicit Reasoning Safety, a vulnerability in LVLMs. Benign combined inputs trigger unsafe LVLM outputs due to flawed or hidden reasoning. To showcase this, we developed Safe Semantics, Unsafe Interpretations, the first dataset for this critical issue. Our demonstrations show that even simple In-Context Learning with SSUI significantly mitigates these implicit multimodal threats, underscoring the urgent need to improve cross-modal implicit reasoning.

Country of Origin
🇨🇳 China

Repos / Data Links

Page Count
3 pages

Category
Computer Science:
Artificial Intelligence