Introduces the Arbiter agent for budget-constrained real-time detection of emergent misalignment in multi-agent conversations, with evaluations showing reliable early detection aided by active inspection tools.
arXiv preprint arXiv:2502.08301 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Sycophancy fine-tuning induces emergent misalignment in LLMs that Alignment Gating can reverse by learning to suppress unsafe representations with generalization from narrow to broad domains.
citing papers explorer
-
The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment
Introduces the Arbiter agent for budget-constrained real-time detection of emergent misalignment in multi-agent conversations, with evaluations showing reliable early detection aided by active inspection tools.
-
Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
Sycophancy fine-tuning induces emergent misalignment in LLMs that Alignment Gating can reverse by learning to suppress unsafe representations with generalization from narrow to broad domains.