PulseAugur
LIVE 04:07:22
research · [2 sources] ·
0
research

LLMs struggle with Ghanaian languages, Nsanku benchmark reveals

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 2 sources

A new benchmark called Nsanku has been developed to evaluate the zero-shot translation capabilities of 19 large language models across 43 Ghanaian languages. The study found that while Gemini 2.5 Flash performed best among proprietary models, and Kimi-K2-Instruct-0905 led open-weight models, no LLM achieved both high performance and high consistency. This indicates that current models are not yet reliable for large-scale translation of these low-resource languages. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Highlights the significant gap in LLM translation capabilities for low-resource African languages, necessitating further research and development.

RANK_REASON This is a research paper presenting a new benchmark for evaluating LLM translation performance on low-resource languages.

Read on arXiv cs.CL →

COVERAGE [2]

  1. arXiv cs.CL TIER_1 · Stephen E. Moore, Mich-Seth Owusu, Akwasi Asare, Lawrence Adu Gyamfi, Paul Azunre, Joel Budu, Jonathan Asiamah, Elias Dzobo, Kelvin Newman, Edmund O. Benefo, Gerhardt Datsomor, Onesimus Addo Appiah, Ama Branoa Banful, Lucas Woedem Kpatah, Saani Mustapha D ·

    Nsanku: Evaluating Zero-Shot Translation Performance of LLMs for Ghanaian Languages

    arXiv:2605.04208v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive multilingual capabilities for well-resourced languages, yet their performance on low-resource African languages remains poorly understood and largely unevaluated. This paper …

  2. arXiv cs.CL TIER_1 · John Ayernor ·

    Nsanku: Evaluating Zero-Shot Translation Performance of LLMs for Ghanaian Languages

    Large language models (LLMs) have demonstrated impressive multilingual capabilities for well-resourced languages, yet their performance on low-resource African languages remains poorly understood and largely unevaluated. This paper presents Nsanku, a systematic benchmark that eva…

RELATED ENTITIES

RELATED TOPICS