EMNLP Paper Tests Five Multimodal AIs on 2,000 Historical Book Illustrations

_akpiper · x · 2026-11-23

A new EMNLP 2026 paper evaluates five multimodal AI models on nearly 2,000 historical children's book illustrations, comparing their interpretations against annotations from thousands of human volunteers.

Related event: Multimodal AI Misreads Individual Historical Illustrations but Nails Group Patterns(2 posts)→

Original post →

More from Multimodal

Multimodal channel →