no code implementations • 20 Sep 2023 • Jinsook Lee, Chris Brooks, Renzhe Yu, Rene Kizilcec
To measure bias, we encourage teams to consider using AUC Gap: the absolute difference between the highest and lowest test AUC for subgroups (e. g., gender, race, SES, prior knowledge).
1 code implementation • 1 May 2023 • Josh Gardner, Renzhe Yu, Quan Nguyen, Christopher Brooks, Rene Kizilcec
We also find that stacked ensembling provides no additional benefits to overall performance or fairness compared to either a local model or the zero-shot transfer procedure we tested.