conftrace_

harmful prompt detection

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (1) multilingual language model (1) harmful content detection (1) cross-modal classification (1) embedding alignment (1) ai safety (1) multimodal learning (1) representation learning (1)

Papers

MULTIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities EMNLP 2025