Can a Prediction’s Rank Offer a More Accurate Quantification of Bias? A Case Study Measuring Sexism in Debiased Language Models

Can a Prediction’s Rank Offer a More Accurate Quantification of Bias? A Case Study Measuring Sexism in Debiased Language Models Jad Doughman author Shady Shehata author Leen Al Qadi author Youssef Nafea author Fakhri Karray author 2023-11 text Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems Daniel Deutsch editor Rotem Dror editor Steffen Eger editor Yang Gao editor Christoph Leiter editor Juri Opitz editor Andreas Rücklé editor Association for Computational Linguistics Bali, Indonesia conference publication doughman-etal-2023-predictions 10.18653/v1/2023.eval4nlp-1.9 https://aclanthology.org/2023.eval4nlp-1.9/ 2023-11 108 116