Frontier LLMs in simulated Greenland sovereignty games escalate more under coercion framing, differ by origin when playing the US role, and achieve peaceful US acquisition in only 1.9% of clean games.
Dual-Layered Political Bias in Large Language Models: Pre- training Priors and RLHF Suppression
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.soc-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Strategic Coercion Within Alliances: The Greenland Sovereignty Game as an AI Stress Test
Frontier LLMs in simulated Greenland sovereignty games escalate more under coercion framing, differ by origin when playing the US role, and achieve peaceful US acquisition in only 1.9% of clean games.