NARCBench and five activation-probing methods detect multi-agent collusion with 0.73-1.00 AUROC across distribution shifts and steganographic tasks by aggregating per-agent signals.
Samuel Marks and Max Tegmark
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
LLMs need metacognition to align expressed uncertainty with their actual knowledge boundaries, moving beyond knowledge expansion to reduce confident errors.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
citing papers explorer
-
Detecting Multi-Agent Collusion Through Multi-Agent Interpretability
NARCBench and five activation-probing methods detect multi-agent collusion with 0.73-1.00 AUROC across distribution shifts and steganographic tasks by aggregating per-agent signals.