Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection

arXiv:2609.18860v1 Announce Type: cross Abstract: When a large vision-language model misclassifies a harmful meme, the failure may reflect missing internal evidence or an inability to route represented evidence to its output. We distinguish these…

Read the full story at arXiv cs.AI ↗