Toxic-bert scores AAE text roughly 1.8x more toxic and 8.8x higher for identity hate than SAE text, and an interactive threshold tool shows how that bias becomes selective censorship.
and Munot, Mousami V
1 Pith paper cite this work, alongside 137 external citations. Polarity classification is still indexing.
1
Pith paper citing it
137
external citations · OpenAlex
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
How AI Fails: An Interactive Pedagogical Tool for Demonstrating Dialectal Bias in Automated Toxicity Models
Toxic-bert scores AAE text roughly 1.8x more toxic and 8.8x higher for identity hate than SAE text, and an interactive threshold tool shows how that bias becomes selective censorship.