SPADE：基于软提示的 AI 生成文本检测框架
SPADE: Soft Prompts for Ai-text DEtection
AI 导读
SPADE 是一个 AI 生成文本检测框架，利用 Pointwise Mutual Information（PMI）衡量提示词对文本的解释程度，并按类别训练软提示来放大区分度，预测最能解释候选文本的类别。与只依赖标注文本或概率分布的现有检测器不同，该方法在多个基准测试中达到 SOTA，尤其在分布外（OOD）数据集上表现出更强的跨数据集迁移能力。
正文 · 原文
Abstract:The easy access to Large Language Models (LLMs) has made AI-generated texts on the web increasingly ubiquitous, making AI-text detection a crucial task. Prompts greatly influence the generation process, but existing detectors focus solely on the generated texts --- supervised methods learn from labeled texts only, and zero-shot methods rely on the text's probability distributions --- ignoring the underlying generation process, which limits their robustness in open-world scenarios. We introduce SPADE: Soft Prompts for Ai-text DEtection, a novel framework for detecting AI-generated text that transfers better across datasets. Specifically, we measure the prompt's influence and use it as a discriminative signal. We characterize the prompt's influence by introducing a Pointwise Mutual Information (PMI) term that captures how much a prompt explains a text. Based on this quantity, SPADE trains one soft prompt per class to amplify the separation, and predicts the class whose prompt best explains the candidate text. Extensive experiments on several benchmarks against various detectors demonstrate the robustness and effectiveness of our method, achieving state-of-the-art (SOTA) performance on out-of-distribution (OOD) datasets.
| Comments: | 24 pages (8 main), 10 figures, 22 tables |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.7 |
| Cite as: | arXiv:2611.16929 [cs.CL] |
| (or arXiv:2611.16929v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16929 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Alex Jiang [view email]
[v1]
Thu, 12 Nov 2026 15:16:19 UTC (683 KB)
来源：arXiv cs.AI · arxiv.org