SOURCE-LINKED INTELLIGENCE

Unveiling Spectral Mechanisms in Training-Free LLM Text Detection

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

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.

Read original source ↗ Open in workspace

recordType

paper

region

Global