Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts

• URL: http://arxiv.org/abs/2605.12890v1
• Date: Wed, 13 May 2026 02:14:21 GMT
• Title: Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts
• Abstract summary: We propose Steer-to-Detect (textttS2D), a framework for detecting large language models (LLMs)<n>In the first stage, textttS2D learns a steering vector that is injected into the hidden states of a frozen observer LLM.<n>In the second stage, detection is performed via a hypothesis testing procedure based on the steered representations.
• Score: 4.404176366651557
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid advancement of large language models (LLMs) has made machine-generated text increasingly difficult to distinguish from human-written text. While recent studies explore leveraging internal representations of language models to uncover deeper detection signals, these raw features often exhibit substantial overlap between classes, limiting their discriminative power. To address this challenge, we propose Steer-to-Detect (\texttt{S2D}), a two-stage framework for detecting LLM-generated text. In the first stage, \texttt{S2D} learns a steering vector that is injected into the hidden states of a frozen observer LLM, producing representations with improved class separability. In the second stage, detection is performed via a hypothesis testing procedure based on the steered representations. We establish finite-sample, high-probability guarantees for Type I and Type II errors, providing a theoretical characterization of the procedure. Empirically, \texttt{S2D} achieves strong and consistent performance across a range of settings, including out-of-distribution scenarios and adversarial perturbations.

Related papers

• The Regularizing Power of Language-Training Deepfake Detectors [57.529452351298495]
  Deepfake detection generally suffers from overfitting to low-level domain-specific artifacts.<n>We use a dual-encoder architecture, pairing a frozen specialist detector with a LoRA-tuned MLLM encoder.<n>We employ a reinforcement learning stage that encourages the model to generate descriptive reasoning before classifying.
  arXiv  Detail & Related papers  (2026-05-29T12:01:17Z)
• Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancement [108.30620357325559]
  Machine-generated texts (MGTs) produced by large language models (LLMs) are increasingly prevalent across various applications.<n>Existing paragraph-level detection methods treat MGTs as entirely machine-like, overlooking the hidden human-like nature of MGTs.<n>We propose a model-agnostic stacked enhancement framework that improves existing detectors by reducing the influence of hidden human-like spans.
  arXiv  Detail & Related papers  (2026-05-22T03:17:21Z)
• Luminol-AIDetect: Fast Zero-shot Machine-Generated Text Detection based on Perplexity under Text Shuffling [9.241565393225953]
  We propose Luminol-AIDetect, a novel, zero-shot statistical approach for machine-generated text (MGT) detection.<n>By applying a simple randomized text-shuffling procedure, we demonstrate that the resulting shift in perplexity serves as a principled, model-agnostic discriminant.<n>We show that Luminol-AIDetect demonstrates state-of-the-art performance, with gains up to 17x lower FPR while being cheaper than prior methods.
  arXiv  Detail & Related papers  (2026-04-28T16:58:55Z)
• DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models [60.713908578319256]
  We propose Direct Discrepancy Learning (DDL) to optimize the detector with task-oriented knowledge.<n>Built upon this, we introduce DetectAnyLLM, a unified detection framework that achieves state-of-the-art MGTD performance.<n>MIRAGE samples human-written texts from 10 corpora across 5 text-domains, which are then re-generated or revised using 17 cutting-edge LLMs.
  arXiv  Detail & Related papers  (2025-09-15T10:59:57Z)
• RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns [50.401907401444404]
  Large language models (LLMs) are crucial for preventing misuse and building trustworthy AI systems.<n>We propose RepreGuard, an efficient statistics-based detection method.<n> Experimental results show that RepreGuard outperforms all baselines with average 94.92% AUROC on both in-distribution (ID) and OOD scenarios.
  arXiv  Detail & Related papers  (2025-08-18T17:59:15Z)
• Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors [77.82885394684202]
  We propose textbfContrastive textbfParaphrase textbfAttack (CoPA), a training-free method that effectively deceives text detectors.<n>CoPA constructs an auxiliary machine-like word distribution as a contrast to the human-like distribution generated by large language models.<n>Our theoretical analysis suggests the superiority of the proposed attack.
  arXiv  Detail & Related papers  (2025-05-21T10:08:39Z)
• Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector [21.19305310480085]
  Deepfake detection is a long-established research topic vital for mitigating the spread of malicious misinformation.<n>We introduce a novel method capable of generating both simultaneously.<n>Our method harnesses the multi-modal learning capability of the pre-trained CLIP and the unprecedented interpretability of large language models.
  arXiv  Detail & Related papers  (2025-03-26T03:28:46Z)
• Unveiling Large Language Models Generated Texts: A Multi-Level Fine-Grained Detection Framework [9.976099891796784]
  Large language models (LLMs) have transformed human writing by enhancing grammar correction, content expansion, and stylistic refinement. Existing detection methods, which mainly rely on single-feature analysis and binary classification, often fail to effectively identify LLM-generated text in academic contexts. We propose a novel Multi-level Fine-grained Detection framework that detects LLM-generated text by integrating low-level structural, high-level semantic, and deep-level linguistic features.
  arXiv  Detail & Related papers  (2024-10-18T07:25:00Z)
• Training-free LLM-generated Text Detection by Mining Token Probability Sequences [18.955509967889782]
  Large language models (LLMs) have demonstrated remarkable capabilities in generating high-quality texts across diverse domains. Training-free methods, which focus on inherent discrepancies through carefully designed statistical features, offer improved generalization and interpretability. We introduce a novel training-free detector, termed textbfLastde that synergizes local and global statistics for enhanced detection.
  arXiv  Detail & Related papers  (2024-10-08T14:23:45Z)
• OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples [44.118047780553006]
  OUTFOX is a framework that improves the robustness of LLM-generated-text detectors by allowing both the detector and the attacker to consider each other's output. Experiments show that the proposed detector improves the detection performance on the attacker-generated texts by up to +41.3 points F1-score. The detector shows a state-of-the-art detection performance: up to 96.9 points F1-score, beating existing detectors on non-attacked texts.
  arXiv  Detail & Related papers  (2023-07-21T17:40:47Z)
• Red Teaming Language Model Detectors with Language Models [114.36392560711022]
  Large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. Recent works have proposed algorithms to detect LLM-generated text and protect LLMs. We study two types of attack strategies: 1) replacing certain words in an LLM's output with their synonyms given the context; 2) automatically searching for an instructional prompt to alter the writing style of the generation.
  arXiv  Detail & Related papers  (2023-05-31T10:08:37Z)
• MAGE: Machine-generated Text Detection in the Wild [82.70561073277801]
  Large language models (LLMs) have achieved human-level text generation, emphasizing the need for effective AI-generated text detection. We build a comprehensive testbed by gathering texts from diverse human writings and texts generated by different LLMs. Despite challenges, the top-performing detector can identify 86.54% out-of-domain texts generated by a new LLM, indicating the feasibility for application scenarios.
  arXiv  Detail & Related papers  (2023-05-22T17:13:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.