A participatory red-teaming project in the Global South created the PLACES dataset of 26k T2I failure examples that reveal unique cultural and linguistic harms missed by existing safety frameworks.
Nathan Matias and Megan Price
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
other 2
citation-polarity summary
fields
cs.CY 2years
2026 2verdicts
UNVERDICTED 2roles
other 1polarities
unclear 1representative citing papers
Case studies with blind UK residents and people from Kerala and Tamil Nadu demonstrate that community input at the systematization stage produces culturally grounded definitions of appropriateness for text-to-image model outputs.
citing papers explorer
-
Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South
A participatory red-teaming project in the Global South created the PLACES dataset of 26k T2I failure examples that reveal unique cultural and linguistic harms missed by existing safety frameworks.
-
Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics
Case studies with blind UK residents and people from Kerala and Tamil Nadu demonstrate that community input at the systematization stage produces culturally grounded definitions of appropriateness for text-to-image model outputs.