RelPPR：基于局部熵波动的黑盒 LLM 生成文本检测方法
Local Entropy Fluctuations for Black-Box LLM-Generated Text Detection
AI 导读
研究者提出新指标 Relative Peak Prominence Rate（RelPPR），利用人类写作信息流平稳、机器生成文本熵局部剧烈波动这一结构差异，实现零样本检测 LLM 生成文本。针对双模型与重采样类检测器在黑盒、指令条件文本上的失效问题，RelPPR 在多模型家族和数据集评估中达到 SOTA，代码已开源。
正文 · 原文
Abstract:Zero-shot detection of machine-generated text is vital for mitigating the risks of large language models (LLMs) misuse. While the state-of-the-art dual-model detectors and resampling-based detectors outperform single-model statistical detectors on unprompted continuations, they suffer a catastrophic breakdown on instruction-conditioned text in the black-box setting, where the source model is unknown. We analyze this failure and trace it to poor prompt conditioning for resampling-based methods and diminished cross-model discrepancy for dual-model detectors. Motivated by recent studies that human writing maintains a steady, uniform information flow, whereas machine-generated text exhibits sharp, localized entropy fluctuations, we propose a new metric, the Relative Peak Prominence Rate (RelPPR) to capture this structural contrast along the entropy trajectory and further leverage it as a signal for LLM-generated text detection. Extensive evaluations across diverse model families and datasets demonstrate that RelPPR achieves state-of-the-art black-box detection performance and remains the most reliable detector under various practical situations. Our code is available at this https URL.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.33767 [cs.AI] |
| (or arXiv:2610.33767v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33767 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xinpeng Wang [view email]
[v1]
Sat, 24 Oct 2026 16:18:20 UTC (913 KB)
来源：arXiv cs.AI · arxiv.org