LLMs encode stereotypes along recoverable geometric axes in attention heads, and two tested LLMs share more stereotype content with each other than with documented human stereotypes.
Proceedings of the AAAI Conference on Artificial Intelligence , author=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
STEREODISCO: Discovering Stereotypicality in LLMs
LLMs encode stereotypes along recoverable geometric axes in attention heads, and two tested LLMs share more stereotype content with each other than with documented human stereotypes.