Proposes a value-encoding framework to characterize and counter homogenization in LLMs by formalizing it via normativity from queer theory and introducing xeno-reproduction tasks from feminist theory, illustrated with a gender-bias experiment on Claude 3.5 Haiku.
Language generation in the limit
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety
Proposes a value-encoding framework to characterize and counter homogenization in LLMs by formalizing it via normativity from queer theory and introducing xeno-reproduction tasks from feminist theory, illustrated with a gender-bias experiment on Claude 3.5 Haiku.