BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization

BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization Ahmed Allam author 2024-08 text Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop) Xiyan Fu editor Eve Fleisig editor Association for Computational Linguistics Bangkok, Thailand conference publication 979-8-89176-097-4 allam-2024-biasdpo 10.18653/v1/2024.acl-srw.7 https://aclanthology.org/2024.acl-srw.7/ 2024-08 42 50