KambadurM.H.M. x 1
bookRéférences 1
Références
" I'm sorry to hear that": finding bias in language models with a holistic descriptor dataset
… By inspection, utterances marked as offensive tend to be those that respond to negative...
Références
" I'm sorry to hear that": finding bias in language models with a holistic descriptor dataset
… By inspection, utterances marked as offensive tend to be those that respond to negative...