Guardado en:
Detalles Bibliográficos
Autores principales: Li, Jinfeng, Chen, Yuefeng, Liu, Xiangyu, Huang, Longtao, Zhang, Rong, Xue, Hui
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2407.08189
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911952690741248
author Li, Jinfeng
Chen, Yuefeng
Liu, Xiangyu
Huang, Longtao
Zhang, Rong
Xue, Hui
author_facet Li, Jinfeng
Chen, Yuefeng
Liu, Xiangyu
Huang, Longtao
Zhang, Rong
Xue, Hui
contents Pre-trained language models (PLMs) have revolutionized both the natural language processing research and applications. However, stereotypical biases (e.g., gender and racial discrimination) encoded in PLMs have raised negative ethical implications for PLMs, which critically limits their broader applications. To address the aforementioned unfairness issues, we present fairBERTs, a general framework for learning fair fine-tuned BERT series models by erasing the protected sensitive information via semantic and fairness-aware perturbations generated by a generative adversarial network. Through extensive qualitative and quantitative experiments on two real-world tasks, we demonstrate the great superiority of fairBERTs in mitigating unfairness while maintaining the model utility. We also verify the feasibility of transferring adversarial components in fairBERTs to other conventionally trained BERT-like models for yielding fairness improvements. Our findings may shed light on further research on building fairer fine-tuned PLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2407_08189
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle fairBERTs: Erasing Sensitive Information Through Semantic and Fairness-aware Perturbations
Li, Jinfeng
Chen, Yuefeng
Liu, Xiangyu
Huang, Longtao
Zhang, Rong
Xue, Hui
Computation and Language
Artificial Intelligence
Pre-trained language models (PLMs) have revolutionized both the natural language processing research and applications. However, stereotypical biases (e.g., gender and racial discrimination) encoded in PLMs have raised negative ethical implications for PLMs, which critically limits their broader applications. To address the aforementioned unfairness issues, we present fairBERTs, a general framework for learning fair fine-tuned BERT series models by erasing the protected sensitive information via semantic and fairness-aware perturbations generated by a generative adversarial network. Through extensive qualitative and quantitative experiments on two real-world tasks, we demonstrate the great superiority of fairBERTs in mitigating unfairness while maintaining the model utility. We also verify the feasibility of transferring adversarial components in fairBERTs to other conventionally trained BERT-like models for yielding fairness improvements. Our findings may shed light on further research on building fairer fine-tuned PLMs.
title fairBERTs: Erasing Sensitive Information Through Semantic and Fairness-aware Perturbations
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2407.08189