2 citations · 4 across the 9 of their papers we have counts for
5 papers · 1 filter
Realistic honeypot evaluations for scheming propensity
Victoria Krakovna, David Lindner, Lewis Ho +2
We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming honeypot evaluations take t…
Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?
Max Kaufmann, David Lindner, Roland S. Zimmermann +1
Chain-of-Thought (CoT) monitoring, in which automated systems monitor the CoT of an LLM, is a promising approach for effectively overseeing AI systems. However, the extent to which…
Consistency Training Helps Stop Sycophancy and Jailbreaks
Alex Irpan, Alexander Matt Turner, Mark Kurzeja +2
An LLM's factuality and refusal training can be compromised by simple changes to a prompt. Models often adopt user beliefs (sycophancy) or satisfy inappropriate requests which are…
A Pragmatic Way to Measure Chain-of-Thought Monitorability
Scott Emmons, Roland S. Zimmermann, David K. Elson +1
While Chain-of-Thought (CoT) monitoring offers a unique opportunity for AI safety, this opportunity could be lost through shifts in training practices or model architecture. To hel…
Evaluating Frontier Models for Stealth and Situational Awareness
Mary Phuong, Roland S. Zimmermann, Ziyue Wang +6
Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavi…