List your company
ResearchFormerly WizWand

Commonsense Reasoning on SWAG (dev)

91.2AccuracyALUM
76.983280.674184.36588.0559Apr 20, 2020Oct 25, 2020May 1, 2021Nov 5, 2021May 12, 2022Nov 16, 2022May 24, 2023
Updated 8mo ago

Evaluation results

MethodLinks
ALUMBackbone=ROBERTA-LARGE, Fine-tuning=SMART2020.0491.2
ALUMBackbone=ROBERTA-LARGE2020.0490.7
Human2020.0488
RoBERTa-SE_largeBackbone=RoBERTa, Model Scale=Large, Training Strategy=Self-Evolution (SE)2023.0584.54
RoBERTa_largeBackbone=RoBERTa, Model Scale=Large, Training Strategy=Vanilla MLM2023.0584.34
BERT-SE_largeBackbone=BERT, Model Scale=Large, Training Strategy=Self-Evolution (SE)2023.0583.61
BERT_largeBackbone=BERT, Model Scale=Large, Training Strategy=Vanilla MLM2023.0583.4
RoBERTa-SE_baseBackbone=RoBERTa, Model Scale=Base, Training Strategy=Self-Evolution (SE)2023.0579.88
RoBERTa_baseBackbone=RoBERTa, Model Scale=Base, Training Strategy=Vanilla MLM2023.0579.69
BERT-SE_baseBackbone=BERT, Model Scale=Base, Training Strategy=Self-Evolution (SE)2023.0577.91
BERT_baseBackbone=BERT, Model Scale=Base, Training Strategy=Vanilla MLM2023.0577.53