Steer-to-Detect learns a steering vector injected into LLM hidden states to boost class separability and applies hypothesis testing with finite-sample Type I/II error guarantees for generated-text detection.
arXiv preprint arXiv:2510.20487 , year =
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Verbalised evaluation awareness in large reasoning models has only small effects on their outputs across safety and alignment tests.
Perplexity differencing on completions from short random prefills surfaces finetuning objectives in the vast majority of tested model organisms across sizes and types.
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.