Guardado en:
Detalles Bibliográficos
Autores principales: Bi, Guanqun, Xie, Yuqiang, Shen, Lei, Cao, Yanan
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2312.15478
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917120294518784
author Bi, Guanqun
Xie, Yuqiang
Shen, Lei
Cao, Yanan
author_facet Bi, Guanqun
Xie, Yuqiang
Shen, Lei
Cao, Yanan
contents The need to assess LLMs for bias and fairness is critical, with current evaluations often being narrow, missing a broad categorical view. In this paper, we propose evaluating the bias and fairness of LLMs from a group fairness lens using a novel hierarchical schema characterizing diverse social groups. Specifically, we construct a dataset, GFAIR, encapsulating target-attribute combinations across multiple dimensions. Moreover, we introduce statement organization, a new open-ended text generation task, to uncover complex biases in LLMs. Extensive evaluations of popular LLMs reveal inherent safety concerns. To mitigate the biases of LLMs from a group fairness perspective, we pioneer a novel chainof-thought method GF-THINK to mitigate biases of LLMs from a group fairness perspective. Experimental results demonstrate its efficacy in mitigating bias and achieving fairness in LLMs. Our dataset and codes are available at https://github.com/surika/Group-Fairness-LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2312_15478
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Group Fairness Lens for Large Language Models
Bi, Guanqun
Xie, Yuqiang
Shen, Lei
Cao, Yanan
Computation and Language
The need to assess LLMs for bias and fairness is critical, with current evaluations often being narrow, missing a broad categorical view. In this paper, we propose evaluating the bias and fairness of LLMs from a group fairness lens using a novel hierarchical schema characterizing diverse social groups. Specifically, we construct a dataset, GFAIR, encapsulating target-attribute combinations across multiple dimensions. Moreover, we introduce statement organization, a new open-ended text generation task, to uncover complex biases in LLMs. Extensive evaluations of popular LLMs reveal inherent safety concerns. To mitigate the biases of LLMs from a group fairness perspective, we pioneer a novel chainof-thought method GF-THINK to mitigate biases of LLMs from a group fairness perspective. Experimental results demonstrate its efficacy in mitigating bias and achieving fairness in LLMs. Our dataset and codes are available at https://github.com/surika/Group-Fairness-LLMs.
title A Group Fairness Lens for Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2312.15478