Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models

Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models Robert Morabito author Jad Kabbara author Ali Emami author 2023-07 text Findings of the Association for Computational Linguistics: ACL 2023 Anna Rogers editor Jordan Boyd-Graber editor Naoaki Okazaki editor Association for Computational Linguistics Toronto, Canada conference publication morabito-etal-2023-debiasing 10.18653/v1/2023.findings-acl.280 https://aclanthology.org/2023.findings-acl.280/ 2023-07 4581 4597