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

arXiv: https://arxiv.org/abs/2606.07313 · HTML: https://mlsanity.com/paper/2606.07313/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Placed in

- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 23 of 23)

- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2401.12070/) (2024)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [RADAR: Robust AI-Text Detection via Adversarial Learning](https://mlsanity.com/paper/2307.03838/) (2023)
- [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020)
- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [MAGE: Machine-generated Text Detection in the Wild](https://mlsanity.com/paper/2305.13242/) (2023)
- [DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text](https://mlsanity.com/paper/2305.17359/) (2023)
- [Testing of Detection Tools for AI-Generated Text](https://mlsanity.com/paper/2306.15666/) (2023)
- [Artificial Text Detection via Examining the Topology of Attention Maps](https://mlsanity.com/paper/2109.04825/) (2021)
- [RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns](https://mlsanity.com/paper/2508.13152/) (2025)
- [Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection](https://mlsanity.com/paper/2412.10432/) (2024)
- [AI-generated text boundary detection with RoFT](https://mlsanity.com/paper/2311.08349/) (2023)
- [Robust AI-Generated Text Detection by Restricted Embeddings](https://mlsanity.com/paper/2410.08113/) (2024)
- [A Practical Examination of AI-Generated Text Detectors for Large Language Models](https://mlsanity.com/paper/2412.05139/) (2024)
- [DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models](https://mlsanity.com/paper/2509.14268/) (2025)
- [PADBen: A Comprehensive Benchmark for Evaluating AI Text Detectors Against Paraphrase Attacks](https://mlsanity.com/paper/2511.00416/) (2025)

## Abstract (arXiv)

Detecting AI-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks. We propose an AI-generated 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 AI-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 AI-generated text detection as a representation-space probing problem and show that steering vectors provide a simple and effective solution.