Machine-generated text detection on RAID (test)
0.2Abstracts FPRLuminol-AIDetect
Evaluation Results
| Method | Links | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Luminol-AIDetectEvaluation protocol=Averaged over 11 generators2026.04 | 0.2 | 15.3 | 0 | 1.5 | 0 | 6.4 | 0 | 1.3 | 0 | 0.3 | 0 | 0 | 0.2 | 0 | 0.1 | 0 | 0.1 | 3.1 | |
| BinocularsEvaluation protocol=Averaged over 11 generators2026.04 | 0.8 | 2.1 | 0.3 | 0.5 | 0 | 2.1 | 0.3 | 2.5 | 0 | 0.2 | 0.8 | 3.7 | 2.1 | 1.1 | 0 | 1.1 | 0.5 | 1.7 | |
| FastDetectEvaluation protocol=Averaged over 11 generators2026.04 | 0.8 | 3.3 | 1.7 | 0.9 | 1.7 | 2.3 | 2.5 | 13.4 | 0.6 | 2.3 | 2 | 10.4 | 2.1 | 1.3 | 2 | 1.5 | 1.7 | 4.4 | |
| Log-LikeEvaluation protocol=Averaged over 11 generators2026.04 | 6.3 | 6.6 | 1.8 | 2.7 | 2.4 | 3.1 | 11.9 | 10.8 | 4.4 | 3 | 6.1 | 6 | 3 | 3.2 | 2.9 | 4.2 | 4.8 | 5 | |
| Log-RankEvaluation protocol=Averaged over 11 generators2026.04 | 7 | 7.1 | 1.5 | 2.6 | 2.7 | 3.7 | 10.4 | 8.6 | 3.9 | 2.2 | 6.4 | 6.3 | 2.9 | 3.2 | 2.4 | 3.6 | 4.6 | 4.7 | |
| GLTREvaluation protocol=Averaged over 11 generators2026.04 | 7.2 | 8.6 | 1.3 | 3.2 | 2.9 | 4 | 10.7 | 8.8 | 7 | 2.2 | 7.2 | 6.1 | 4 | 3.6 | 3.2 | 4 | 5.4 | 5.1 | |
| LRREvaluation protocol=Averaged over 11 generators2026.04 | 8.3 | 14 | 1.1 | 5.3 | 3.7 | 8.1 | 6.9 | 12.1 | 3.3 | 4.8 | 5.8 | 10.3 | 3.6 | 6 | 1.8 | 6.2 | 4.3 | 8.4 | |
| EntropyEvaluation protocol=Averaged over 11 generators2026.04 | 21.6 | 20.3 | 16.4 | 15.3 | 22.5 | 20.1 | 16.7 | 17.1 | 10.7 | 7.9 | 17.4 | 14.1 | 21.2 | 18.3 | 19.4 | 23.2 | 18.2 | 17 | |
| RankEvaluation protocol=Averaged over 11 generators2026.04 | 26.3 | 13.7 | 10.1 | 8.1 | 22.6 | 14.4 | 23.5 | 11.2 | 29.1 | 17.9 | 22.7 | 11.6 | 15.6 | 10.9 | 16.5 | 11.3 | 20.8 | 12.4 |