Skip to Main Content
Table 12: 
Cross-model micro-averaged accuracy (%). The first row is the model to test, and the second row is the model on which prompt weights are learned.
TestBERT-baseBERT-large
Trainbaselargelargebase
Mine 38.9 38.7 43.7 42.2 
Mine+Man 39.6 40.1 43.9 42.2 
Mine+Para 36.2 35.6 40.1 39.0 
Man+Para 37.3 35.6 38.8 37.5 
TestBERT-baseBERT-large
Trainbaselargelargebase
Mine 38.9 38.7 43.7 42.2 
Mine+Man 39.6 40.1 43.9 42.2 
Mine+Para 36.2 35.6 40.1 39.0 
Man+Para 37.3 35.6 38.8 37.5 
Close Modal

or Create an Account

Close Modal
Close Modal