Your Fairness May Vary: Pretrained Language Model Fairness in Toxic Text ClassificationIoana Baldini SoaresDennis Weiet al.2022ACL 2022
Domain Representative Keywords Selection: A Probabilistic ApproachPritom AkashJie Huanget al.2022ACL 2022
Towards Generalizable Methods for Automating Risk Score CalculationJennifer J. LiangEric Lehmeret al.2022ACL 2022