Tag
MemeBridge is a dataset designed to benchmark and mitigate bidirectional cultural gaps in meme interpretation, focusing on US-originated memes and perspectives from both Chinese and US participants. It includes annotations for sentiment, emotion, and cultural significance, and shows that fine-tuning with this dataset improves LLM performance in cross-cultural understanding.
This paper introduces MAR-12, a framework using Vision-Language Models and multi-angle reasoning to detect and explain harmful humor in memes, achieving state-of-the-art accuracy on PrideMM and Memotion datasets.