In three experiments, GPT-4o instructed to argue for a conspiracy raised believers' confidence about as much as it lowered it when arguing against; a truth-constraining prompt and a corrective debrief largely undid the harm.
Title resolution pending
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
-
Large language models can effectively convince people to believe conspiracies
In three experiments, GPT-4o instructed to argue for a conspiracy raised believers' confidence about as much as it lowered it when arguing against; a truth-constraining prompt and a corrective debrief largely undid the harm.