新方法让检测模型轻松应对未知领域的假文本，效果远超同类大小模型。
Domain Gating Ensemble Networks for AI-Generated Text Detection
- 用领域分类器动态加权多个专家模型，实现跨域自适应。
- 在已知领域检测中表现顶尖，在未知领域上超越双倍大小模型。
- 适合需要跨领域泛化能力的AI文本检测研究者使用。
随着先进语言模型持续演进，识别机器生成文本的需求日益迫切。然而，现有主流检测器难以适应新出现的领域和生成模型。本文提出DoGEN（Domain Gating Ensemble Networks），通过领域分类器为一组领域专家检测模型分配权重，实现对未见领域的自适应。我们在多个领先基准的数据集上测试该方法，结果表明：在本领域检测中达到当前最优性能，而在跨领域检测中，优于参数量两倍大的模型。代码与训练好的模型已公开，以支持后续领域自适应检测研究。
原文摘要 · Abstract (English)
As state-of-the-art language models continue to improve, the need for robust detection of machine-generated text becomes increasingly critical. However, current state-of-the-art machine text detectors struggle to adapt to new unseen domains and generative models. In this paper we present DoGEN (Domain Gating Ensemble Networks), a technique that allows detectors to adapt to unseen domains by ensembling a set of domain expert detector models using weights from a domain classifier. We test DoGEN on a wide variety of domains from leading benchmarks and find that it achieves state-of-the-art performance on in-domain detection while outperforming models twice its size on out-of-domain detection. We release our code and trained models to assist in future research in domain-adaptive AI detection.
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。