Training interventions reshape rather than eliminate calibration and abstention disparities in toxicity detection, requiring a multi-axis fairness framework.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fair and Calibrated Toxicity Detection with Robust Training and Abstention
Training interventions reshape rather than eliminate calibration and abstention disparities in toxicity detection, requiring a multi-axis fairness framework.