Across 16 open-weight language models, gender is encoded as a sex-linked binary, transgender and nonbinary terms are less probable than random nouns, and mental illness is more probable after those terms; these effects grow with model size.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Gender Trouble in Language Models: An Empirical Audit Guided by Gender Performativity Theory
Across 16 open-weight language models, gender is encoded as a sex-linked binary, transgender and nonbinary terms are less probable than random nouns, and mental illness is more probable after those terms; these effects grow with model size.