In emergency scenes, text-to-image models skew who appears and who helps, favoring men, middle-aged, and lighter-skinned people, and a soft-token tweak reduces the gap.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MM 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EmergencyBias: Bias in Text-to-Image Models under Emergency Scenarios
In emergency scenes, text-to-image models skew who appears and who helps, favoring men, middle-aged, and lighter-skinned people, and a soft-token tweak reduces the gap.