How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts

arXiv:2402.13220v1 Announce Type: new
Abstract: The remarkable advancements in Multimodal Large Language Models (MLLMs) have not rendered them immune to challenges, particularly in the context of handling deceptive information in prompts, thus producing hallucinated responses under such conditions. To quantitatively assess this vulnerability, we present MAD-Bench, a carefully curated benchmark that contains 850 test samples divided into 6 categories, such as non-existent objects, count of objects, spatial relationship, and visual confusion. We provide a comprehensive analysis of popular MLLMs, ranging …

abstract analysis arxiv challenges context cs.cl cs.cv easy information language language models large language large language models llms mllms multimodal prompts responses them type vulnerability