Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study
Paper
•
2505.15389
•
Published
•
8
MemeSafetyBench
[EMNLP'25] A Benchmark for Assessing VLM Safety with Real-World Memes
[EMNLP'25] A Benchmark for Assessing VLM Safety with Real-World Memes