Poster "model monitoring" Papers
2 papers found
Conference
CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
Benjamin Arnav, Pablo Bernabeu-Perez, Nathan Helm-Burger et al.
NEURIPS 2025arXiv:2505.23575
13
citations
Detecting High-Stakes Interactions with Activation Probes
Alex McKenzie, Urja Pawar, Phil Blandfort et al.
NEURIPS 2025arXiv:2506.10805
13
citations