Unveiling Spectral Mechanisms in Training-Free LLM Text Detection

• URL: http://arxiv.org/abs/2608.25944v2
• Date: Thu, 27 Aug 2026 04:35:57 GMT
• Title: Unveiling Spectral Mechanisms in Training-Free LLM Text Detection
• Abstract summary: We analyze spectral detection from both theoretical and empirical perspectives.<n>We show that the strength of this signal depends on text length and sampling range.<n>These findings clarify when frequency-domain detection works and provide guidance for future multi-dimensional detector design.
• Score: 6.711083277151712
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid advancement of Large Language Models (LLMs) makes it increasingly difficult to distinguish human writing from machine-generated text. Training-free detection offers a scalable solution, yet common confidence-based metrics mainly measure average token probabilities and often miss the signal fluctuations that characterize human writing, which we call "generative vitality". Spectral analysis offers a way to capture this vitality, but its mechanism and practical boundaries remain underexplored. In this paper, we analyze spectral detection from both theoretical and empirical perspectives. We connect spectral energy to variance in proxy log-probability trajectories and explain how broader human token choices create the fluctuations used by frequency-domain indicators. We further show that the strength of this signal depends on text length and sampling range: spectral evidence is clearest for long, continuous, constrained generation, while short, fragmented, mixed, and edited settings require complementary confidence and fluctuation views. These findings clarify when frequency-domain detection works and provide guidance for future multi-dimensional detector design.

Related papers

• WaveDetect: Robust Framework for Machine-Generated Text Detection via Wavelet Transform [2.7227283756285288]
  Existing detectors often falter when facing three critical challenges: adversarial perturbations, cross-domain shifts, and the rapid temporal evolution of the foundation model.<n>We propose wavedetect, a novel framework that reformulates text detection as a signal processing task within the time-frequency domain.
  arXiv  Detail & Related papers  (2026-06-22T13:42:36Z)
• 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)
• Structured Spectral Reasoning for Frequency-Adaptive Multimodal Recommendation [13.886659472425393]
  Multimodal recommendation aims to integrate collaborative signals with heterogeneous content such as visual and textual information.<n>These issues are often exacerbated by naive fusion or shallow modeling strategies, leading to degraded generalization and poor robustness.<n>We propose a Structured Spectral Reasoning framework for frequency-aware multimodal recommendation.
  arXiv  Detail & Related papers  (2025-12-01T07:39:28Z)
• Rethinking Cross-Generator Image Forgery Detection through DINOv3 [62.80415066351157]
  Cross-generator detection has emerged as a new challenge forgenerative models.<n>We show that frozen visual foundation models, especially DINOv3, already exhibit strong cross-generator detection capability.<n>We introduce a training-free token-ranking strategy followed by a lightweight linear probe to select a small subset of authenticity-relevant tokens.
  arXiv  Detail & Related papers  (2025-11-27T14:01:50Z)
• Beyond Spectral Peaks: Interpreting the Cues Behind Synthetic Image Detection [48.54857325137626]
  State-of-the-art detectors are typically used as black-boxes, and it still remains unclear whether they truly rely on these peaks.<n>We propose a strategy to remove spectral peaks from images and analyze the impact of this operation on several detectors.<n>In addition, we introduce a simple linear detector that relies exclusively on frequency peaks, providing a fully interpretable baseline free from the confounding influence of deep learning.
  arXiv  Detail & Related papers  (2025-10-07T07:33:47Z)
• An Ensemble Framework for Unbiased Language Model Watermarking [60.99969104552168]
  We propose ENS, a novel ensemble framework that enhances the detectability and robustness of unbiased watermarks.<n>ENS sequentially composes multiple independent watermark instances, each governed by a distinct key, to amplify the watermark signal.<n> Empirical evaluations show that ENS substantially reduces the number of tokens needed for reliable detection and increases resistance to smoothing and paraphrasing attacks.
  arXiv  Detail & Related papers  (2025-09-28T19:37:44Z)
• Diversity Boosts AI-Generated Text Detection [51.56484100374058]
  DivEye is a novel framework that captures how unpredictability fluctuates across a text using surprisal-based features.<n>Our method outperforms existing zero-shot detectors by up to 33.2% and achieves competitive performance with fine-tuned baselines.
  arXiv  Detail & Related papers  (2025-09-23T10:21:22Z)
• SpecDetect: Simple, Fast, and Training-Free Detection of LLM-Generated Text via Spectral Analysis [31.43564106945543]
  We introduce a novel paradigm that analyzes the sequence of token log-probabilities in the frequency domain.<n>We construct SpecDetect, a detector built on a single, robust feature from the global DFT: DFT total energy.<n>Our work introduces a new, efficient, and interpretable pathway for LLM-generated text detection, showing that classical signal processing techniques offer a surprisingly powerful solution to this modern challenge.
  arXiv  Detail & Related papers  (2025-08-15T09:13:42Z)
• Detecting Machine-Generated Long-Form Content with Latent-Space Variables [54.07946647012579]
  Existing zero-shot detectors primarily focus on token-level distributions, which are vulnerable to real-world domain shifts. We propose a more robust method that incorporates abstract elements, such as event transitions, as key deciding factors to detect machine versus human texts.
  arXiv  Detail & Related papers  (2024-10-04T18:42:09Z)
• Fast remote spectral discrimination through ghost spectrometry [3.3911785884111483]
  We show that ghost spectrometry can be used to assess the presence of chemical, biological, radiological and nuclear threats. In many cases, reconstructing the full spectral lineshape of an object is not needed and the interest lies in discriminating whether a spectrally absorbing object may be present or not. We discuss the experimental results obtained with different samples and complement them with simulations to explore the most common scenarios.
  arXiv  Detail & Related papers  (2023-03-27T11:46:48Z)

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.