New benchmark reveals multilingual safety gaps in vision-language models

Researchers have developed MLingualFC, a new multilingual benchmark to test the safety vulnerabilities of vision-language models (VLMs). This benchmark uses flowchart images encoded with harmful instructions in five languages: Hindi, Punjabi, Spanish, Romanian, and German. Evaluations of models like Qwen2.5-VL, Gemma-4, and Pangea revealed that visual attacks are highly successful in Latin-script languages, indicating current safety measures do not generalize well across languages and modalities. AI

影响 Highlights the need for more robust, multilingual safety alignment in advanced AI models.

排序理由 The cluster contains an academic paper introducing a new benchmark for evaluating AI model safety. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• Gemma-4
• MLingualFC
• Pangea
• Qwen2.5-VL

• 论文
• 安全

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →