MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?

arXiv:2406.17806v1 Announce Type: cross
Abstract: Humans are prone to cognitive distortions -- biased thinking patterns that lead to exaggerated responses to specific stimuli, albeit in very different contexts. This paper demonstrates that advanced Multimodal Large Language Models (MLLMs) exhibit similar tendencies. While these models are designed to respond queries under safety mechanism, they sometimes reject harmless queries in the presence of certain visual stimuli, disregarding the benign nature of their contexts. As the initial step in investigating this behavior, we …

arxiv cs.ai cs.cl cs.cr cs.cv cs.lg language multimodal safe