List your company

OOD Detection on WMT15 En-Fr (ID) IT (OOD) (test)

97.41AUROCAP-OOD
73.95880.046586.13592.2235Feb 5, 2026

Evaluation results

MethodLinks
AP-OODOOD level=Input, Learning paradigm=Supervised, Backbone=Transformer (base)2026.0297.4116.89
Deep SADOOD level=Input, Learning paradigm=Supervised, Backbone=Transformer (base)2026.0297.1917.37
AP-OODOOD level=Output, Learning paradigm=Supervised, Backbone=Transformer (base)2026.0297.1419.52
AP-OODBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Input, Unsupervised=true2026.0295.6121.85
Binary logitsOOD level=Input, Learning paradigm=Supervised, Backbone=Transformer (base)2026.0295.4220.51
KNNBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Output, Unsupervised=true2026.0295.0531.95
AP-OODBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Output, Unsupervised=true2026.0294.4426.42
Binary logitsOOD level=Output, Learning paradigm=Supervised, Backbone=Transformer (base)2026.0294.428.68
KNNBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Input, Unsupervised=true2026.0294.2535
MahalanobisBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Input, Unsupervised=true2026.0293.2837.8
Deep SVDDBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Input, Unsupervised=true2026.0292.1546.28
Deep SADOOD level=Output, Learning paradigm=Supervised, Backbone=Transformer (base)2026.0291.4951.8
PerplexityBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Output, Unsupervised=true2026.0291.3444.94
MahalanobisBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Output, Unsupervised=true2026.0291.0754.49
Deep SVDDBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Output, Unsupervised=true2026.0289.5757.89
Relative MahalanobisOOD level=Input, Learning paradigm=Supervised, Backbone=Transformer (base)2026.0288.2129.06
Relative MahalanobisOOD level=Output, Learning paradigm=Supervised, Backbone=Transformer (base)2026.0287.6837.33
EntropyBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Output, Unsupervised=true2026.0274.8668.69