DEER: 面向可泛化机器生成文本检测的实例自适应路由解耦专家混合模型
DEER: Disentangled Mixture of Experts with Instance-Adaptive Routing for Generalizable Machine-Generated Text Detection
AI总结:
提出DEER框架,通过解耦领域局部与领域不变知识为专门专家模块,并利用强化学习驱动的路由器基于实例级检测奖励选择专家路径,解决机器生成文本检测中的领域偏移问题,在域内和域外数据集上均取得优于现有方法的性能。
摘要:
随着LLM的快速发展,检测机器生成文本已成为一项关键挑战,但现有检测器在领域偏移下性能严重下降。通过系统性的初步研究,我们将这一脆弱性归因于当前泛化策略中的两个根本缺陷:即多领域训练中领域特定知识的不完全保留,以及推理时知识检索与检测目标之间的错位。为解决这些问题,我们提出了DEER,一种解耦的专家混合框架,将领域局部和领域不变知识明确解耦到专门的专家模块中。与静态领域匹配不同,DEER采用强化学习驱动的路由器,基于实例级检测奖励选择专家路径。这种任务对齐、领域无关的机制通过优先考虑检测效用而非风格相似性,确保了对未见分布的鲁棒适应。大量实验表明,DEER始终优于最先进的检测器,在域内和域外数据集上平均F1提升1.28%和2.92%,准确率提升1.35%和2.26%,为开放世界部署提供了可靠的泛化能力。
英文摘要:
Detecting machine-generated text has become a critical challenge amid the rapid advancement of LLMs, yet existing detectors degrade severely under domain shift. Through systematic pilot studies, we trace this vulnerability to two fundamental flaws in current generalization strategies, namely the incomplete preservation of domain-specific knowledge during multi-domain training and the misalignment between knowledge retrieval and the detection objective at inference. To address these gaps, we propose DEER, a Disentangled mixturE-of-ExpeRts framework that explicitly decouples domain-local and domain-invariant knowledge into specialized expert modules. Instead of static domain matching, DEER employs a reinforcement learning-driven router that selects expert pathways based on instance-level detection rewards. This task-aligned, domain-agnostic mechanism ensures robust adaptation to unseen distributions by prioritizing detection utility over stylistic resemblance. Extensive experiments demonstrate that DEER consistently outperforms state-of-the-art detectors, achieving average F1 improvements of 1.28% and 2.92%, and accuracy gains of 1.35% and 2.26% on in-domain and out-of-domain datasets, offering reliable generalization for open-world deployment.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。