Small language models sustain political personas and become more ideologically extreme when replying to counter-arguments, according to a language-model judge.
We need a new ethics for a world of AI agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
AI Propaganda factories with language models
Small language models sustain political personas and become more ideologically extreme when replying to counter-arguments, according to a language-model judge.