Compliance-forcing instructions cause up to 30 percentage point drops in metacognitive accuracy across most frontier models, while removing the compliance element restores performance and Constitutional AI shows near-immunity.
PacifAIst: Benchmarking AI agent safety.arXiv preprint arXiv:2508.09762
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Compliance Trap: How Structural Constraints Degrade Frontier AI Metacognition Under Adversarial Pressure
Compliance-forcing instructions cause up to 30 percentage point drops in metacognitive accuracy across most frontier models, while removing the compliance element restores performance and Constitutional AI shows near-immunity.