A Parameter-Efficient Multi-Objective Approach to Mitigate Stereotypical Bias in Language Models

A Parameter-Efficient Multi-Objective Approach to Mitigate Stereotypical Bias in Language Models Yifan Wang author Vera Demberg author 2024-08 text Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP) Agnieszka Faleńska editor Christine Basta editor Marta Costa-jussà editor Seraphina Goldfarb-Tarrant editor Debora Nozza editor Association for Computational Linguistics Bangkok, Thailand conference publication wang-demberg-2024-parameter 10.18653/v1/2024.gebnlp-1.1 https://aclanthology.org/2024.gebnlp-1.1/ 2024-08 1 19