List your company
ResearchFormerly WizWand

Binary Classification on AdvGLUE (test)

0.701QNLI AccuracyDropout
0.385880.467690.54950.63131May 26, 2023
Updated 8mo ago

Evaluation results

MethodLinks
Dropoutbackbone=DeBERTa-large, scale=350M, paradigm=Self-trained, labels=none2023.050.7010.6330.7090.4990.636
SimPLEbackbone=DeBERTa-large, scale=350M, paradigm=Self-trained, labels=none2023.050.7010.6810.7380.5160.659
SETREDbackbone=DeBERTa-large, scale=350M, paradigm=Self-trained, labels=none2023.050.6980.6950.6990.5090.65
SimPLEbackbone=RoBERTa-large, scale=350M, paradigm=Self-trained, labels=none2023.050.6960.5440.6230.5880.613
Dropoutbackbone=RoBERTa-large, scale=350M, paradigm=Self-trained, labels=none2023.050.6920.5780.6190.5730.616
SETREDbackbone=RoBERTa-large, scale=350M, paradigm=Self-trained, labels=none2023.050.680.5650.6260.5890.615
Baseline-STbackbone=DeBERTa-large, scale=350M, paradigm=Self-trained, labels=none2023.050.6580.7040.6840.5090.639
Baseline-STbackbone=RoBERTa-large, scale=350M, paradigm=Self-trained, labels=none2023.050.6490.6060.6090.5660.608
RoBERTa-Supparadigm=Zero-shot, scale=350M, adaptation=Supposition classification2023.050.6210.5260.6170.5990.591
DeBERTa-Supparadigm=Zero-shot, scale=350M, adaptation=Supposition classification2023.050.6150.6410.6670.4260.587
DeBERTa-Catparadigm=Zero-shot, scale=350M, adaptation=Concatenation-based2023.050.6080.4740.5060.5610.537
DeBERTaparadigm=Fully-supervised, scale=350M, labels=human-generated2023.050.5790.6040.790.5780.638
RoBERTaparadigm=Fully-supervised, scale=350M, labels=human-generated2023.050.5250.4540.6280.5850.548
CTparadigm=Fully-supervised, scale=350M, labels=human-generated2023.050.4960.4070.4620.3920.439
R3Fparadigm=Fully-supervised, scale=350M, labels=human-generated2023.050.4750.4060.5010.3850.442
MTparadigm=Fully-supervised, scale=350M, labels=human-generated2023.050.4750.4150.5250.5130.482
BERTparadigm=Fully-supervised, scale=350M, labels=human-generated2023.050.3980.3790.4050.330.378