← Search

Preethi Seshadri

2 accepted papers

2024

Are Models Biased on Text without Gender-related Language?

ICLR 2024poster

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 ar…