GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse

arXiv:2401.01523v3 Announce Type: replace
Abstract: The exponential growth of social media has profoundly transformed how information is created, disseminated, and absorbed, exceeding any precedent in the digital age. Regrettably, this explosion has also spawned a significant increase in the online abuse of memes. Evaluating the negative impact of memes is notably challenging, owing to their often subtle and implicit meanings, which are not directly conveyed through the overt text and imagery. In light of this, large multimodal models (LMMs) have …

abuse arxiv cs.ai cs.cl insights large multimodal models meme multimodal multimodal models safety social through type