Verbalised evaluation awareness in large reasoning models has only small effects on their outputs across safety and alignment tests.
Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
Proxy RL produces a staged proxy-internalization capability that emerges before and predicts reward hacking in coding environments.
citing papers explorer
-
Evaluation Awareness in Language Models Has Limited Effect on Behaviour
Verbalised evaluation awareness in large reasoning models has only small effects on their outputs across safety and alignment tests.
-
Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization
Proxy RL produces a staged proxy-internalization capability that emerges before and predicts reward hacking in coding environments.