Year: 2026
Type: conference-paper
Abstract: Distinguishing machine-generated text (MGT) from human-written text (HWT) becomes increasingly important due to potential misuse.However, most supervised detectors often degrade out-of-domain (OOD) and require large, diverse training sets.In this work, we analyze the linearity and quality of MGT representations and show that simple linear probes outperform a wide range of detectors while being substantially more sample-efficient.We first show that MGT and HWT latent representations are linearly separable in low-dimensional space, and provide a plausible explanation for this separability through systematic differences in their representation quality.Motivated by these insights, we train two variants of simple linear probes and evaluate them across 4 benchmarks against 16 baselines.Probes consistently improve OOD detection (+11 AUC), requiring solely <100 samples to reach nearpeak performance.We show that this transferability arises because probes recover a shared latent MGT direction that generalizes across diverse settings.Finally, we demonstrate that probing vectors capture a continuous spectrum of "machineness", highlighting their potential for fine-grained estimation of AI-edited text.Overall, our work provides insights into latentspace differences between MGT and HWT and demonstrates the potential of linear probes as as robust and sample-efficient MGT detectors.We release our code on github.
Institutions: King's College London, Wikimedia Foundation
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7204221856