Unequal Voices: How LLMs Construct Constrained Queer Narratives
This work addresses the problem of AI-driven marginalization in discourse for queer communities, highlighting a specific bias in LLM outputs.
The study investigated how large language models (LLMs) generate constrained and stereotyped narratives about queer people, finding that LLMs significantly limit portrayals of queer personas in terms of harmful representations, narrow topics, and discursive othering.
One way social groups are marginalized in discourse is that the narratives told about them often default to a narrow, stereotyped range of topics. In contrast, default groups are allowed the full complexity of human existence. We describe the constrained representations of queer people in LLM generations in terms of harmful representations, narrow representations, and discursive othering and formulate hypotheses to test for these phenomena. Our results show that LLMs are significantly limited in their portrayals of queer personas.