LLMs show low endorsement of persuasion-infused messages unless given partisan personas, which then increase polarized endorsements varying by technique and topic.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Political Persuasion and Endorsement in Large Language Models
LLMs show low endorsement of persuasion-infused messages unless given partisan personas, which then increase polarized endorsements varying by technique and topic.