AIBullisharXiv – CS AI · Mar 96/10
🧠
MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing
Researchers developed MAP (Map-Level Attention Processing), a training-free method to reduce hallucinations in Large Vision-Language Models by treating hidden states as 2D semantic maps. The approach uses attention-based operations to better leverage factual information and improve consistency between generated text and visual inputs.