打造一站式机器生成文本检测评估平台，解决评测碎片化问题。
MGTEVAL: An Interactive Platform for Systemtic Evaluation of Machine-Generated Text Detectors
- 四步流程整合数据构建、攻击注入、模型训练与评估
- 支持12种文本攻击，可配置大模型生成检测样本
- 提供网页和命令行接口，免代码实现对比实验
我们提出MGTEVAL，一个可扩展的系统性评估机器生成文本（MGT）检测器的平台。尽管MGT检测技术快速进展，现有评估仍分散于不同数据集、预处理方法、攻击方式和评价指标之间，导致结果难以比较和复现。MGTEVAL将工作流程分为四个模块：数据集构建、数据集攻击、检测器训练和性能评估。平台支持通过可配置的大语言模型生成MGT，对测试集应用12种文本攻击，通过统一接口训练检测器，并报告检测效果、鲁棒性和效率。平台提供命令行和基于Web的界面，用户无需重写代码即可便捷实验。
原文摘要 · Abstract (English)
We present MGTEVAL, an extensible platform for systematic evaluation of Machine-Generated Text (MGT) detectors. Despite rapid progress in MGT detection, existing evaluations are often fragmented across datasets, preprocessing, attacks, and metrics, making results hard to compare and reproduce. MGTEVAL organizes the workflow into four components: Dataset Building, Dataset Attack, Detector Training, and Performance Evaluation. It supports constructing custom benchmarks by generating MGT with configurable LLMs, applying 12 text attacks to test sets, training detectors via a unified interface, and reporting effectiveness, robustness, and efficiency. The platform provides both command-line and Web-based interfaces for user-friendly experimentation without code rewriting.
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。