Small language models sustain political personas and become more ideologically extreme when replying to counter-arguments, according to a language-model judge.
Goldstein and Brett V
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 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.