Wei Cai
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models
According to the abstract excerpt, the authors propose SAFE-PRO, which has a multimodal model ask safety-focused clarifying questions when an image and text together are ambiguous. They report better safety than a baseline, about half the over-refusal, and higher average single-turn safety than two named commercial models.