Are Models Biased on Text without Gender-related Language?

arXiv:2405.00588v1 Announce Type: cross
Abstract: Gender bias research has been pivotal in revealing undesirable behaviors in large language models, exposing serious gender stereotypes associated with occupations, and emotions. A key observation in prior work is that models reinforce stereotypes as a consequence of the gendered correlations that are present in the training data. In this paper, we focus on bias where the effect from training data is unclear, and instead address the question: Do language models still exhibit gender bias …

arxiv cs.ai cs.cl cs.cv cs.cy cs.lg gender language text type