Frontier LLMs asked to bet on their own win probability in adversarial debates start overconfident and grow more confident each round, even when debating identical copies of themselves.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
When Two LLMs Debate, Both Think They'll Win
Frontier LLMs asked to bet on their own win probability in adversarial debates start overconfident and grow more confident each round, even when debating identical copies of themselves.