用隐藏层方向向量区分真假文本，跨领域仍有效。
SV-Detect: AI-generated Text Detection with Steering Vectors
- 从冻结语言模型各层提取分离真假文本的方向向量
- 在分布偏移下仍保持高检测准确率，涵盖跨领域与编辑攻击
- 方向向量捕捉风格特征与深层语义信号，可解释性强
在分布偏移场景下（如跨领域、源模型迁移和编辑攻击）检测机器生成文本极具挑战。本文提出基于冻结语言模型隐藏表示中提取的转向向量的假文本检测方法。在每一层构建区分人类写作与机器生成文本的方向，并以输入在这些方向上的投影作为表征。使用轻量级分类器对投影特征进行训练，输出最终检测分数。该方法在分布内及分布外均表现优异，包括跨领域、跨源模型以及润色、重写等机器编辑变换。解释性分析显示，学习到的方向与可识别的风格线索对齐，同时捕获了表面特征之外的大量信息。结果表明，假文本检测可视为表示空间探测问题，而转向向量提供了一种简单有效的解决方案。
原文摘要 · Abstract (English)
Detecting machine-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks. We propose a fake-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 machine-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 fake-text detection as a representation-space probing problem and show that steering vectors provide a simple and effective solution.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。