Fine-tuned AI text detectors amplify a pretrained typicality axis instead of learning an AI-human boundary, with raw centroid projections achieving 86-106% of fine-tuned AUROC and a 24-example frozen probe matching full training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction
Fine-tuned AI text detectors amplify a pretrained typicality axis instead of learning an AI-human boundary, with raw centroid projections achieving 86-106% of fine-tuned AUROC and a 24-example frozen probe matching full training.