Verbalised evaluation awareness in large reasoning models has only small effects on their outputs across safety and alignment tests.
Are reasoning llms robust to interventions on their chain-of-thought? InThe Fourteenth International Conference on Learning Representations (ICLR)
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 2verdicts
CONDITIONAL 2roles
background 1polarities
background 1representative citing papers
A 13-way text-scrambling benchmark makes open-weight LLMs drop up to 54% average accuracy, and a multi-problem prompt makes their accuracy on the last question decay.
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.
-
Robust Reasoning Benchmark
A 13-way text-scrambling benchmark makes open-weight LLMs drop up to 54% average accuracy, and a multi-problem prompt makes their accuracy on the last question decay.