@inproceedings{tiwari-etal-2026-sample,
title = "Sample-Size Scaling of the {A}frican Languages {NLI} Evaluation",
author = "Tiwari, Anuj and
Ogunremu, Oluwapelumi and
Oko-odion, Terry and
Egbewale, Jesujuwon and
Nwokocha, Hannah Sopuruchi",
editor = "Chimoto, Everlyn Asiko and
Lignos, Constantine and
Muhammad, Shamsuddeen and
Abdulmumin, Idris and
Siro, Clemencia and
Adelani, David Ifeoluwa",
booktitle = "Proceedings of the 7th Workshop on {A}frican Natural Language Processing ({A}frica{NLP} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.africanlp-main.22/",
pages = "217--227",
ISBN = "979-8-89176-364-7",
abstract = "African languages have very little labelled data, and it is unclear if augmenting the quantity of annotation data reliably enhances downstream performance. The study is a systematic sample-size scaling study of natural language inference (NLI) on 16 African languages based on the AfriXNLI benchmark. Under controlled conditions, two multilingual transformer models with roughly 0.6B parameters XLM-R Large fine-tuned on XNLI and AfroXLM-R Large are tested on sample sizes of between 50 and 500 labeled examples and average their results across random subsampling runs. As opposed to the usual belief of monotonic increase with increased data, we find a strongly language-sensitive and often non-monotonic scaling behavior. Some languages show early saturation or decrease in performance with sample size as well as high variance in low resource regimes. These results indicate that the volume of data is not enough to guarantee stable profits to African NLI, creating the necessity of language-sensitive datasets creation and stronger multi-lingual modelling strategies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tiwari-etal-2026-sample">
<titleInfo>
<title>Sample-Size Scaling of the African Languages NLI Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Tiwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oluwapelumi</namePart>
<namePart type="family">Ogunremu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terry</namePart>
<namePart type="family">Oko-odion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujuwon</namePart>
<namePart type="family">Egbewale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="given">Sopuruchi</namePart>
<namePart type="family">Nwokocha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on African Natural Language Processing (AfricaNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Everlyn</namePart>
<namePart type="given">Asiko</namePart>
<namePart type="family">Chimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamsuddeen</namePart>
<namePart type="family">Muhammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Idris</namePart>
<namePart type="family">Abdulmumin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clemencia</namePart>
<namePart type="family">Siro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-364-7</identifier>
</relatedItem>
<abstract>African languages have very little labelled data, and it is unclear if augmenting the quantity of annotation data reliably enhances downstream performance. The study is a systematic sample-size scaling study of natural language inference (NLI) on 16 African languages based on the AfriXNLI benchmark. Under controlled conditions, two multilingual transformer models with roughly 0.6B parameters XLM-R Large fine-tuned on XNLI and AfroXLM-R Large are tested on sample sizes of between 50 and 500 labeled examples and average their results across random subsampling runs. As opposed to the usual belief of monotonic increase with increased data, we find a strongly language-sensitive and often non-monotonic scaling behavior. Some languages show early saturation or decrease in performance with sample size as well as high variance in low resource regimes. These results indicate that the volume of data is not enough to guarantee stable profits to African NLI, creating the necessity of language-sensitive datasets creation and stronger multi-lingual modelling strategies.</abstract>
<identifier type="citekey">tiwari-etal-2026-sample</identifier>
<location>
<url>https://aclanthology.org/2026.africanlp-main.22/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>217</start>
<end>227</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sample-Size Scaling of the African Languages NLI Evaluation
%A Tiwari, Anuj
%A Ogunremu, Oluwapelumi
%A Oko-odion, Terry
%A Egbewale, Jesujuwon
%A Nwokocha, Hannah Sopuruchi
%Y Chimoto, Everlyn Asiko
%Y Lignos, Constantine
%Y Muhammad, Shamsuddeen
%Y Abdulmumin, Idris
%Y Siro, Clemencia
%Y Adelani, David Ifeoluwa
%S Proceedings of the 7th Workshop on African Natural Language Processing (AfricaNLP 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-364-7
%F tiwari-etal-2026-sample
%X African languages have very little labelled data, and it is unclear if augmenting the quantity of annotation data reliably enhances downstream performance. The study is a systematic sample-size scaling study of natural language inference (NLI) on 16 African languages based on the AfriXNLI benchmark. Under controlled conditions, two multilingual transformer models with roughly 0.6B parameters XLM-R Large fine-tuned on XNLI and AfroXLM-R Large are tested on sample sizes of between 50 and 500 labeled examples and average their results across random subsampling runs. As opposed to the usual belief of monotonic increase with increased data, we find a strongly language-sensitive and often non-monotonic scaling behavior. Some languages show early saturation or decrease in performance with sample size as well as high variance in low resource regimes. These results indicate that the volume of data is not enough to guarantee stable profits to African NLI, creating the necessity of language-sensitive datasets creation and stronger multi-lingual modelling strategies.
%U https://aclanthology.org/2026.africanlp-main.22/
%P 217-227
Markdown (Informal)
[Sample-Size Scaling of the African Languages NLI Evaluation](https://aclanthology.org/2026.africanlp-main.22/) (Tiwari et al., AfricaNLP 2026)
ACL
- Anuj Tiwari, Oluwapelumi Ogunremu, Terry Oko-odion, Jesujuwon Egbewale, and Hannah Sopuruchi Nwokocha. 2026. Sample-Size Scaling of the African Languages NLI Evaluation. In Proceedings of the 7th Workshop on African Natural Language Processing (AfricaNLP 2026), pages 217–227, Rabat, Morocco. Association for Computational Linguistics.