Tinted Frames: Question Framing Blinds Vision-Language Models
davidhalladay.github.io
Tinted Frames: Question Framing Blinds Vision-Language Models
1–2 of 2 posts
Re: Tinted Frames: Question Framing Blinds Vision-Language Models
#2VLMs are selectively blind — they decide how much to look at an image based on question framing (open-ended vs Yes/No vs MCQ), even when the same visual reasoning is required.