LLM translation quality reaches acceptable human scores for Hausa but remains poor for Fongbe, automatic metrics show weak human correlation especially for Hausa due to neural embedding collapse, and at least 2,500 sentences are required for stable system rankings.
English2Gbe: A multilingual machine translation model for Fon/Ewe Gbe.arXiv preprint arXiv:2112.11482,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evaluating Large Language Models for Hausa and Fongbe Machine Translation: Benchmarks, Failures, and Metric Reliability
LLM translation quality reaches acceptable human scores for Hausa but remains poor for Fongbe, automatic metrics show weak human correlation especially for Hausa due to neural embedding collapse, and at least 2,500 sentences are required for stable system rankings.