Machine-Generated Text Detection on XSum In-Domain (IND-MGT)
91.7AccuracyDEER
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DEERBackbone=RoBERTa-base, Detection Methodology Category=Domain generalization methods2025.11 | 91.7 | 91.67 | |
| RobertaBackbone=RoBERTa-base, Detection Methodology Category=Model-based methods2025.11 | 88.77 | 89.61 | |
| ImBDDetection Methodology Category=Model-based methods2025.11 | 88.77 | 88.85 | |
| MGT-PrismBackbone=RoBERTa-base, Detection Methodology Category=Domain generalization methods2025.11 | 88.76 | 89.02 | |
| PeCoLABackbone=RoBERTa-base, Detection Methodology Category=Model-based methods2025.11 | 88.67 | 88.57 | |
| EAGLEBackbone=RoBERTa-base, Detection Methodology Category=Model-based methods2025.11 | 88.08 | 89.25 | |
| MSCLBackbone=RoBERTa-base, Detection Methodology Category=Domain generalization methods2025.11 | 87.5 | 88.12 | |
| MoSEsDetection Methodology Category=Model-based methods2025.11 | 86.39 | 86.14 | |
| TACITDetection Methodology Category=Domain generalization methods2025.11 | 85.23 | 85.76 | |
| GhostbusterDetection Methodology Category=Model-based methods2025.11 | 82.44 | 81.84 | |
| BinocularsBackbone=GPT-2 Small (124M), Detection Methodology Category=Metric-based methods2025.11 | 71.77 | 66.77 | |
| Fast-DetectGPTBackbone=GPT-2 Small (124M), Detection Methodology Category=Metric-based methods2025.11 | 51.17 | 54.01 |