LLMs Reproduce Stereotypes of Sexual and Gender Minorities

2025/01/10 by Ostrow, Ruby, Lopez, Adam
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2501.05926

Abstract

A large body of research has found substantial gender bias in NLP systems. Most of this research takes a binary, essentialist view of gender: limiting its variation to the categories _men_ and _women_, conflating gender with sex, and ignoring different sexual identities. But gender and sexuality exist on a spectrum, so in this paper we study the biases of large language models (LLMs) towards sexual and gender minorities beyond binary categories. Grounding our study in a widely used social psychology model -- the Stereotype Content Model -- we demonstrate that English-language survey questions about social perceptions elicit more negative stereotypes of sexual and gender minorities from both humans and LLMs. We then extend this framework to a more realistic use case: text generation. Our analysis shows that LLMs generate stereotyped representations of sexual and gender minorities in this setting, showing that they amplify representational harms in creative writing, a widely advertised use for LLMs.

Related

• Queer People are People First: Deconstructing Sexual Identity Stereotypes in Large Language Models
• Protected group bias and stereotypes in Large Language Models
• From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs
• Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddings
• Theories of "Sexuality" in Natural Language Processing Bias Research