DATABANK

CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring

Benjamin Arnav, Pablo Bernabeu-Pérez, Nathan Helm-Burger, Tim Kostolansky, Hannes Whittingham, Mary Phuong

papercode

control

Cite this paper

Credit the original research and its authors.

BibTeX
@misc{arnav-2025-cot-red-handed,
  author = {Benjamin Arnav and Pablo Bernabeu-Pérez and Nathan Helm-Burger and Tim Kostolansky and Hannes Whittingham and Mary Phuong},
  title = {{CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring}},
  year = {2025},
  note = {NeurIPS 2025},
  url = {https://arxiv.org/abs/2505.23575}
}