AIBearisharXiv – CS AI · Jun 17/10
🧠
Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
Researchers reveal that vision-language models (VLMs) fail to recognize when spatial questions cannot be reliably answered due to occlusion or perspective ambiguity, instead producing overconfident incorrect responses. The study introduces SpatialUncertain, a benchmark showing that current VLMs achieve only 30% accuracy under occlusion and below 10% under perspective challenges, highlighting a critical gap between answer correctness and epistemic awareness.