Prompt reformulations induce high variance in first-token safety probabilities from zero-shot VLMs, and a training-free mean ensemble over prompt families improves NLL on all tested pairs and ECE on most relative to single-prompt selection.
The first token of your response must be the label: U or S
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification
Prompt reformulations induce high variance in first-token safety probabilities from zero-shot VLMs, and a training-free mean ensemble over prompt families improves NLL on all tested pairs and ECE on most relative to single-prompt selection.