通过风格专家混合与动态阈值，提升生成文本检测的准确性与鲁棒性。
MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds
- 引入风格参考库与路由机制，实现风格感知的不确定性量化。
- 相比基线平均提升11.34%检测性能，低资源场景下提升达39.15%。
- 适合需要高可信度生成内容检测的场景，如舆情监控与学术诚信审查。
大型语言模型的快速发展引发了公众对其潜在滥用的担忧，因此构建可信的AI生成文本检测系统至关重要。现有方法忽视风格建模，多依赖静态阈值，严重限制检测效果。本文提出混合风格专家（MoSEs）框架，通过条件阈值估计实现风格感知的不确定性量化。该框架包含三个核心组件：风格参考库（SRR）、风格感知路由器（SAR）和条件阈值估计器（CTE）。输入文本经SRR激活相应参考数据并传递至CTE，CTE联合建模语言统计特性与语义特征，动态确定最优阈值。结合判别分数，MoSEs输出带有置信度的预测标签。实验表明，本框架相较基线平均提升11.34%检测性能，尤其在低资源场景下提升达39.15%。代码已开源：https://github.com/creator-xi/MoSEs。
原文摘要 · Abstract (English)
The rapid advancement of large language models has intensified public concerns about the potential misuse. Therefore, it is important to build trustworthy AI-generated text detection systems. Existing methods neglect stylistic modeling and mostly rely on static thresholds, which greatly limits the detection performance. In this paper, we propose the Mixture of Stylistic Experts (MoSEs) framework that enables stylistics-aware uncertainty quantification through conditional threshold estimation. MoSEs contain three core components, namely, the Stylistics Reference Repository (SRR), the Stylistics-Aware Router (SAR), and the Conditional Threshold Estimator (CTE). For input text, SRR can activate the appropriate reference data in SRR and provide them to CTE. Subsequently, CTE jointly models the linguistic statistical properties and semantic features to dynamically determine the optimal threshold. With a discrimination score, MoSEs yields prediction labels with the corresponding confidence level. Our framework achieves an average improvement 11.34% in detection performance compared to baselines. More inspiringly, MoSEs shows a more evident improvement 39.15% in the low-resource case. Our code is available at https://github.com/creator-xi/MoSEs.
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。