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.
ChatGPT MT: Competitive for High-(but not Low-) Resource Languages
3 Pith papers cite this work, alongside 5 external citations. Polarity classification is still indexing.
3
Pith papers citing it
5
external citations · external index
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 3years
2026 3roles
background 1polarities
background 1representative citing papers
Concept Separation Curves provide a classifier-independent method to visualize and quantify how sentence embeddings distinguish conceptual meaning from syntactic variations across languages and domains.
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.
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.
-
Finding Meaning in Embeddings: Concept Separation Curves
Concept Separation Curves provide a classifier-independent method to visualize and quantify how sentence embeddings distinguish conceptual meaning from syntactic variations across languages and domains.
-
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.