Table 7 

The TPR-GAP results for all versions (Balanced, Gentle, and Aggressive) for the three concepts where we have ground truth (Adjectives, Gender, and Race).

ExperimentAdjectivesGenderRace
Balanced 0.057 0.003 0.002 
Gentle 0.074 0.014 0.012 
Aggressive 0.012 0.003 0.049 
ExperimentAdjectivesGenderRace
Balanced 0.057 0.003 0.002 
Gentle 0.074 0.014 0.012 
Aggressive 0.012 0.003 0.049 
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. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.
Accept