A toxicity model trained without identity-targeting comments has similar overall AUC but worse per-subgroup accuracy than a model trained on mixed data, especially on false negatives.
Limitations of Pinned AUC for Measuring Unintended Bias
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This report examines the Pinned AUC metric introduced and highlights some of its limitations. Pinned AUC provides a threshold-agnostic measure of unintended bias in a classification model, inspired by the ROC-AUC metric. However, as we highlight in this report, there are ways that the metric can obscure different kinds of unintended biases when the underlying class distributions on which bias is being measured are not carefully controlled.
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Debiasing Personal Identities in Toxicity Classification
A toxicity model trained without identity-targeting comments has similar overall AUC but worse per-subgroup accuracy than a model trained on mixed data, especially on false negatives.