'Rarely' a problem? Language models exhibit inverse scaling in their predictions following 'few'-type quantifiers

Add code
Dec 16, 2022
Figure 1 for 'Rarely' a problem? Language models exhibit inverse scaling in their predictions following 'few'-type quantifiers
Figure 2 for 'Rarely' a problem? Language models exhibit inverse scaling in their predictions following 'few'-type quantifiers
Figure 3 for 'Rarely' a problem? Language models exhibit inverse scaling in their predictions following 'few'-type quantifiers
Figure 4 for 'Rarely' a problem? Language models exhibit inverse scaling in their predictions following 'few'-type quantifiers

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: