How Murky Before a VLM Knows It Cannot See? Accuracy, Confidence and Abstention on a Physical Visibility Axis
Robustness studies of vision-language models (VLMs) grade degradation on nominal severity scales ("level 1-5") that carry no physical units, and they rarely ask whether a model's confidence follows the loss of visibility. We measure accuracy, internal (token-probability) confidence, verbalized confidence and an explici...
Mochamad Rizal Fauzan, Irgi Surya
· 0 citations