Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SV-Detect: AI-generated Text Detection with Steering Vectors

About

Detecting machine-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks. We propose a fake-text detector based on steering vectors extracted from the hidden representations of a frozen language model. At each layer, we construct a direction that separates human-written from machine-generated text, and represent each input by its layer-wise alignment with these directions. A lightweight classifier trained on these projection features yields the final detection score. Our method achieves strong performance both in-distribution and under distribution shift, including across domains, source models, and machine-editing transformations such as polishing and rewriting. Interpretation analyses show that the learned directions align with recognizable stylistic cues while capturing substantial additional signal beyond surface features. These results position fake-text detection as a representation-space probing problem and show that steering vectors provide a simple and effective solution.

Mikhail Vishnyakov, Tatiana Gaintseva• 2026

Related benchmarks

TaskDatasetResultRank
Machine-generated text detectionCOLING MGT English 2025
Macro F184.8
41
AI-generated text detectionDetectRL Multi-LLM--
27
AI-generated text detectionDetectRL Multi-Domain--
27
Machine-generated text detectionDetectRL GPT-3.5
AUROC99.99
16
Machine-generated text detectionDetectRL Llama-2
AUROC99.99
16
Machine-generated text detectionDetectRL Direct Attack
AUROC99.99
16
Machine-generated text detectionDetectRL Prompt Attack
AUROC99.96
16
Machine-generated text detectionDetectRL Paraphrase Attack
AUROC99.98
16
Machine-generated text detectionDetectRL Perturbation Attack
AUROC99.99
16
Machine-generated text detectionDetectRL Mixing Attack
AUROC (%)99.83
16
Showing 10 of 17 rows

Other info

Follow for update