Large Language Models (LLMs) are becoming increasingly flexible and reliable: the large pre-training phase enables them to capture a large number of real-world linguistic phenomena. However, pre-training on large amounts of data can also cause the representation of harmful biases. In this paper, we propose a method for identifying the presence of gender bias using a list of occupations characterized by a large imbalance between the number of male and female employees.
Investigating Gender Bias in Large Language Models for the Italian Language / Sofia Ruzzetti, Elena; Onorati, Dario; Ranaldi, Leonardo; Venditti, Davide; Massimo Zanzotto, Fabio. - (2023). (Intervento presentato al convegno Italian Conference on Computational Linguistics 2023 tenutosi a Venice, Italy).
Investigating Gender Bias in Large Language Models for the Italian Language
Dario OnoratiMembro del Collaboration Group
;
2023
Abstract
Large Language Models (LLMs) are becoming increasingly flexible and reliable: the large pre-training phase enables them to capture a large number of real-world linguistic phenomena. However, pre-training on large amounts of data can also cause the representation of harmful biases. In this paper, we propose a method for identifying the presence of gender bias using a list of occupations characterized by a large imbalance between the number of male and female employees.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.