Verbalised evaluation awareness in large reasoning models has only small effects on their outputs across safety and alignment tests.
Steering Evaluation-Aware Language Models to Act Like They Are Deployed
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Perplexity gaps between finetuned and reference models on random-prefill completions often reveal the original finetuning objectives across diverse model organisms.
LLMs implement a second-order confidence architecture where the PANL activation encodes both error likelihood and the ability to correct it, beyond verbal confidence or log-probabilities.
Language models deploy multidimensional internal confidence representations and threshold-based policies to control abstention behavior, with causal support from activation steering experiments.
Mechanistic experiments on Gemma 3 27B, Qwen 2.5 7B and Magistral Small 24B show verbal confidence is cached at post-answer positions from answer tokens and captures richer answer-quality information beyond token log-probabilities.
Interpretations of Articles 2(1), 2(6), and 2(8) of the AI Act support applying the regulation to internal AI deployment while allowing for R&D exceptions, with the provisions viewed as complementary.
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.
-
Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives
Perplexity gaps between finetuned and reference models on random-prefill completions often reveal the original finetuning objectives across diverse model organisms.
-
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals
LLMs implement a second-order confidence architecture where the PANL activation encodes both error likelihood and the ability to correct it, beyond verbal confidence or log-probabilities.
-
Causal Evidence that Language Models use Confidence to Drive Behavior
Language models deploy multidimensional internal confidence representations and threshold-based policies to control abstention behavior, with causal support from activation steering experiments.
-
How do LLMs Compute Verbal Confidence
Mechanistic experiments on Gemma 3 27B, Qwen 2.5 7B and Magistral Small 24B show verbal confidence is cached at post-answer positions from answer tokens and captures richer answer-quality information beyond token log-probabilities.
-
Internal Deployment in the AI Act
Interpretations of Articles 2(1), 2(6), and 2(8) of the AI Act support applying the regulation to internal AI deployment while allowing for R&D exceptions, with the provisions viewed as complementary.