Skip to Main Content
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 
Close Modal

or Create an Account

Close Modal
Close Modal