Table 3: 

Knowledge and consistency results. Best model for each measure in bold.

ModelAccuracyConsistencyConsistent-Acc
majority 23.1±21.0 100.0±0.0 23.1±21.0 
 
BERT-base 45.8±25.6 58.5±24.2 27.0±23.8 
BERT-large 48.1±26.1 61.1 ±23.0 29.5 ±26.6 
BERT-large-wwm 48.7 ±25.0 60.9±24.2 29.3±26.9 
 
RoBERTa-base 39.0±22.8 52.1±17.8 16.4±16.4 
RoBERTa-large 43.2±24.7 56.3±20.4 22.5±21.1 
 
ALBERT-base 29.8±22.8 49.8±20.1 16.7±20.3 
ALBERT-xxlarge 41.7±24.9 52.1±22.4 23.8±24.8 
ModelAccuracyConsistencyConsistent-Acc
majority 23.1±21.0 100.0±0.0 23.1±21.0 
 
BERT-base 45.8±25.6 58.5±24.2 27.0±23.8 
BERT-large 48.1±26.1 61.1 ±23.0 29.5 ±26.6 
BERT-large-wwm 48.7 ±25.0 60.9±24.2 29.3±26.9 
 
RoBERTa-base 39.0±22.8 52.1±17.8 16.4±16.4 
RoBERTa-large 43.2±24.7 56.3±20.4 22.5±21.1 
 
ALBERT-base 29.8±22.8 49.8±20.1 16.7±20.3 
ALBERT-xxlarge 41.7±24.9 52.1±22.4 23.8±24.8 
View Large
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy.
Accept