cs.AI, cs.CL, cs.CV, cs.LG

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs

arXiv:2604.08846v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) have been shown to be vulnerable to malicious queries that can elicit unsafe responses. Recent work uses prompt engineering, response classification, or finetunin…