Sentence-level AI-generated text detection on MOSAIC Aggregated
94Average F1 ScoreSenFlow
Evaluation results
| Method | Links | |
|---|---|---|
| SenFlowType=TB, Evaluation Protocol=Unified2026.06 | 94 | |
| SenDetEXType=TB, Evaluation Protocol=Unified2026.06 | 92.4 | |
| SeqXGPTType=TB, Evaluation Protocol=Unified2026.06 | 80.6 | |
| POGERType=TB, Evaluation Protocol=Unified2026.06 | 77.6 | |
| BinocularsType=TF, Evaluation Protocol=Unified, Threshold tuning strategy=single threshold tuned on the combined validation set2026.06 | 66.7 | |
| Fast-DetectGPTType=TF, Evaluation Protocol=Unified, Threshold tuning strategy=single threshold tuned on the combined validation set2026.06 | 58.1 |