@inproceedings{adebara-etal-2025-evaluating,
title = "Where Are We? Evaluating {LLM} Performance on {A}frican Languages",
author = "Adebara, Ife and
Toyin, Hawau Olamide and
Ghebremichael, Nahom Tesfu and
Elmadany, AbdelRahim A. and
Abdul-Mageed, Muhammad",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1572/",
doi = "10.18653/v1/2025.acl-long.1572",
pages = "32704--32731",
ISBN = "979-8-89176-251-0",
abstract = "Africa{'}s rich linguistic heritage remains underrepresented in NLP, largely due to historical policies that favor foreign languages and create significant data inequities. In this paper, we integrate theoretical insights on Africa{'}s language landscape with an empirical evaluation using Sahara{---} a comprehensive benchmark curated from large-scale, publicly accessible datasets capturing the continent{'}s linguistic diversity. By systematically assessing the performance of leading large language models (LLMs) on Sahara, we demonstrate how policy-induced data variations directly impact model effectiveness across African languages. Our findings reveal that while a few languages perform reasonably well, many Indigenous languages remain marginalized due to sparse data. Leveraging these insights, we offer actionable recommendations for policy reforms and inclusive data practices. Overall, our work underscores the urgent need for a dual approach{---}combining theoretical understanding with empirical evaluation{---}to foster linguistic diversity in AI for African communities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adebara-etal-2025-evaluating">
<titleInfo>
<title>Where Are We? Evaluating LLM Performance on African Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ife</namePart>
<namePart type="family">Adebara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hawau</namePart>
<namePart type="given">Olamide</namePart>
<namePart type="family">Toyin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nahom</namePart>
<namePart type="given">Tesfu</namePart>
<namePart type="family">Ghebremichael</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Africa’s rich linguistic heritage remains underrepresented in NLP, largely due to historical policies that favor foreign languages and create significant data inequities. In this paper, we integrate theoretical insights on Africa’s language landscape with an empirical evaluation using Sahara— a comprehensive benchmark curated from large-scale, publicly accessible datasets capturing the continent’s linguistic diversity. By systematically assessing the performance of leading large language models (LLMs) on Sahara, we demonstrate how policy-induced data variations directly impact model effectiveness across African languages. Our findings reveal that while a few languages perform reasonably well, many Indigenous languages remain marginalized due to sparse data. Leveraging these insights, we offer actionable recommendations for policy reforms and inclusive data practices. Overall, our work underscores the urgent need for a dual approach—combining theoretical understanding with empirical evaluation—to foster linguistic diversity in AI for African communities.</abstract>
<identifier type="citekey">adebara-etal-2025-evaluating</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1572</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1572/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>32704</start>
<end>32731</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Where Are We? Evaluating LLM Performance on African Languages
%A Adebara, Ife
%A Toyin, Hawau Olamide
%A Ghebremichael, Nahom Tesfu
%A Elmadany, AbdelRahim A.
%A Abdul-Mageed, Muhammad
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F adebara-etal-2025-evaluating
%X Africa’s rich linguistic heritage remains underrepresented in NLP, largely due to historical policies that favor foreign languages and create significant data inequities. In this paper, we integrate theoretical insights on Africa’s language landscape with an empirical evaluation using Sahara— a comprehensive benchmark curated from large-scale, publicly accessible datasets capturing the continent’s linguistic diversity. By systematically assessing the performance of leading large language models (LLMs) on Sahara, we demonstrate how policy-induced data variations directly impact model effectiveness across African languages. Our findings reveal that while a few languages perform reasonably well, many Indigenous languages remain marginalized due to sparse data. Leveraging these insights, we offer actionable recommendations for policy reforms and inclusive data practices. Overall, our work underscores the urgent need for a dual approach—combining theoretical understanding with empirical evaluation—to foster linguistic diversity in AI for African communities.
%R 10.18653/v1/2025.acl-long.1572
%U https://aclanthology.org/2025.acl-long.1572/
%U https://doi.org/10.18653/v1/2025.acl-long.1572
%P 32704-32731
Markdown (Informal)
[Where Are We? Evaluating LLM Performance on African Languages](https://aclanthology.org/2025.acl-long.1572/) (Adebara et al., ACL 2025)
ACL
- Ife Adebara, Hawau Olamide Toyin, Nahom Tesfu Ghebremichael, AbdelRahim A. Elmadany, and Muhammad Abdul-Mageed. 2025. Where Are We? Evaluating LLM Performance on African Languages. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 32704–32731, Vienna, Austria. Association for Computational Linguistics.