Nsanku benchmark shows current LLMs achieve only modest zero-shot translation scores on 43 Ghanaian languages, with no model reaching both high average performance and high cross-language consistency.
Low resource Twi-English parallel corpus for machine translation in multiple domains (Twi-2-ENG)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
ACCEPT 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Nsanku: Evaluating Zero-Shot Translation Performance of LLMs for Ghanaian Languages
Nsanku benchmark shows current LLMs achieve only modest zero-shot translation scores on 43 Ghanaian languages, with no model reaching both high average performance and high cross-language consistency.