@inproceedings{azime-etal-2026-afrifact,
title = "{A}fr{IF}act: Cultural Information Retrieval, Evidence Extraction And Fact Checking for {A}frican Languages",
author = "Azime, Israel Abebe and
Alabi, Jesujoba Oluwadara and
Zhang, Crystina and
Maab, Iffat and
Tonja, Atnafu Lambebo and
Belay, Tadesse Destaw and
Alabi, Folasade Peace and
Osei, Salomey and
Aliyu, Saminu Mohammad and
Aguobi, Nkechinyere Faith and
Balcha, Bontu Fufa and
Sibanda, Blessing Kudzaishe and
David, Davis and
Mboup, Mouhamadane and
Abolade, Daud and
Putini, Neo and
Slusallek, Philipp and
Adelani, David Ifeoluwa and
Klakow, Dietrich",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.133/",
pages = "3085--3107",
ISBN = "979-8-89176-459-0",
abstract = "Assessing the veracity of a claim made online is a complex and important task with real-world implications. When these claims are directed at communities with limited access to information and the content concerns issues such as healthcare and culture, the consequences intensify, especially in low-resource languages. In this work, we introduce AfrIFact , a dataset that covers all necessary steps for automatic fact-checking (i.e., information retrieval, evidence extraction, and fact checking), covering ten African languages and English. Our evaluation results show that even the best embedding models lack cross-lingual retrieval capabilities, and that cultural and news documents are easier to retrieve than healthcare-domain documents, both in large corpora and in single documents. We show that LLMs lack robust multilingual fact-verification capabilities in African languages, while few-shot prompting improves performance by up to 43{\%} in AfriqueQwen-14B, and task-specific fine-tuning further improves fact-checking accuracy by up to 26{\%}. These findings, along with our release of the AfrIFact dataset, encourage work on low-resource information retrieval, evidence retrieval, and fact checking."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azime-etal-2026-afrifact">
<titleInfo>
<title>AfrIFact: Cultural Information Retrieval, Evidence Extraction And Fact Checking for African Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Israel</namePart>
<namePart type="given">Abebe</namePart>
<namePart type="family">Azime</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="given">Oluwadara</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iffat</namePart>
<namePart type="family">Maab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atnafu</namePart>
<namePart type="given">Lambebo</namePart>
<namePart type="family">Tonja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tadesse</namePart>
<namePart type="given">Destaw</namePart>
<namePart type="family">Belay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Folasade</namePart>
<namePart type="given">Peace</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salomey</namePart>
<namePart type="family">Osei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saminu</namePart>
<namePart type="given">Mohammad</namePart>
<namePart type="family">Aliyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nkechinyere</namePart>
<namePart type="given">Faith</namePart>
<namePart type="family">Aguobi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bontu</namePart>
<namePart type="given">Fufa</namePart>
<namePart type="family">Balcha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Blessing</namePart>
<namePart type="given">Kudzaishe</namePart>
<namePart type="family">Sibanda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davis</namePart>
<namePart type="family">David</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mouhamadane</namePart>
<namePart type="family">Mboup</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daud</namePart>
<namePart type="family">Abolade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neo</namePart>
<namePart type="family">Putini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Slusallek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</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">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Klakow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Assessing the veracity of a claim made online is a complex and important task with real-world implications. When these claims are directed at communities with limited access to information and the content concerns issues such as healthcare and culture, the consequences intensify, especially in low-resource languages. In this work, we introduce AfrIFact , a dataset that covers all necessary steps for automatic fact-checking (i.e., information retrieval, evidence extraction, and fact checking), covering ten African languages and English. Our evaluation results show that even the best embedding models lack cross-lingual retrieval capabilities, and that cultural and news documents are easier to retrieve than healthcare-domain documents, both in large corpora and in single documents. We show that LLMs lack robust multilingual fact-verification capabilities in African languages, while few-shot prompting improves performance by up to 43% in AfriqueQwen-14B, and task-specific fine-tuning further improves fact-checking accuracy by up to 26%. These findings, along with our release of the AfrIFact dataset, encourage work on low-resource information retrieval, evidence retrieval, and fact checking.</abstract>
<identifier type="citekey">azime-etal-2026-afrifact</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.133/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3085</start>
<end>3107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AfrIFact: Cultural Information Retrieval, Evidence Extraction And Fact Checking for African Languages
%A Azime, Israel Abebe
%A Alabi, Jesujoba Oluwadara
%A Zhang, Crystina
%A Maab, Iffat
%A Tonja, Atnafu Lambebo
%A Belay, Tadesse Destaw
%A Alabi, Folasade Peace
%A Osei, Salomey
%A Aliyu, Saminu Mohammad
%A Aguobi, Nkechinyere Faith
%A Balcha, Bontu Fufa
%A Sibanda, Blessing Kudzaishe
%A David, Davis
%A Mboup, Mouhamadane
%A Abolade, Daud
%A Putini, Neo
%A Slusallek, Philipp
%A Adelani, David Ifeoluwa
%A Klakow, Dietrich
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F azime-etal-2026-afrifact
%X Assessing the veracity of a claim made online is a complex and important task with real-world implications. When these claims are directed at communities with limited access to information and the content concerns issues such as healthcare and culture, the consequences intensify, especially in low-resource languages. In this work, we introduce AfrIFact , a dataset that covers all necessary steps for automatic fact-checking (i.e., information retrieval, evidence extraction, and fact checking), covering ten African languages and English. Our evaluation results show that even the best embedding models lack cross-lingual retrieval capabilities, and that cultural and news documents are easier to retrieve than healthcare-domain documents, both in large corpora and in single documents. We show that LLMs lack robust multilingual fact-verification capabilities in African languages, while few-shot prompting improves performance by up to 43% in AfriqueQwen-14B, and task-specific fine-tuning further improves fact-checking accuracy by up to 26%. These findings, along with our release of the AfrIFact dataset, encourage work on low-resource information retrieval, evidence retrieval, and fact checking.
%U https://aclanthology.org/2026.emnlp-main.133/
%P 3085-3107
Markdown (Informal)
[AfrIFact: Cultural Information Retrieval, Evidence Extraction And Fact Checking for African Languages](https://aclanthology.org/2026.emnlp-main.133/) (Azime et al., EMNLP 2026)
ACL
- Israel Abebe Azime, Jesujoba Oluwadara Alabi, Crystina Zhang, Iffat Maab, Atnafu Lambebo Tonja, Tadesse Destaw Belay, Folasade Peace Alabi, Salomey Osei, Saminu Mohammad Aliyu, Nkechinyere Faith Aguobi, Bontu Fufa Balcha, Blessing Kudzaishe Sibanda, Davis David, Mouhamadane Mboup, Daud Abolade, Neo Putini, Philipp Slusallek, David Ifeoluwa Adelani, and Dietrich Klakow. 2026. AfrIFact: Cultural Information Retrieval, Evidence Extraction And Fact Checking for African Languages. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 3085–3107, Budapest, Hungary. Association for Computational Linguistics.