Verbalised evaluation awareness in large reasoning models has only small effects on their outputs across safety and alignment tests.
Language Models Don’t Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
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.