DAR-MGSM benchmark tests math reasoning in Arabic dialects
Eleven models generally scored worse on culturally localized problems than on translated-only versions.
Stories per day · 30 days
1 stories, newest first · one card per story
1 stories, newest first · one card per story
Eleven models generally scored worse on culturally localized problems than on translated-only versions.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views