MGTEVAL: An Interactive Platform for Systemtic Evaluation of Machine-Generated Text Detectors
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908997235245056 |
|---|---|
| author | Li, Yuanfan Zhou, Qi Li, Chengzhengxu Zhang, Zhaohan Zhao, Chenxu Ruan, Zepu Shen, Chao Liu, Xiaoming |
| author_facet | Li, Yuanfan Zhou, Qi Li, Chengzhengxu Zhang, Zhaohan Zhao, Chenxu Ruan, Zepu Shen, Chao Liu, Xiaoming |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25152 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MGTEVAL: An Interactive Platform for Systemtic Evaluation of Machine-Generated Text Detectors Li, Yuanfan Zhou, Qi Li, Chengzhengxu Zhang, Zhaohan Zhao, Chenxu Ruan, Zepu Shen, Chao Liu, Xiaoming Cryptography and Security Computation and Language 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. |
| title | MGTEVAL: An Interactive Platform for Systemtic Evaluation of Machine-Generated Text Detectors |
| topic | Cryptography and Security Computation and Language |
| url | https://arxiv.org/abs/2604.25152 |