@inproceedings{tairu-adebesin-2026-evaluating,
title = "Evaluating Retrieval-Augmented Generation for Medication Question Answering on {N}igerian Drug Labels in {Y}or{\`u}b{\'a}",
author = "Tairu, Zainab and
Adebesin, Aramide",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Plum, Alistair and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the Second Workshop on Language Models for Low-Resource Languages ({L}o{R}es{LM} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.loreslm-1.8/",
pages = "90--97",
ISBN = "979-8-89176-377-7",
abstract = "Large Language Models (LLMs) have the potential to improve healthcare information access in Nigeria, but they risk generating unsafe or inaccurate responses when used in low-resource languages such as Yor{\`u}b{\'a}. Retrieval-Augmented Generation (RAG) has since emerged as a promising approach to mitigate hallucinations by grounding LLM outputs in verified knowledge sources. To assess its effectiveness in low-resource contexts, we construct a controlled Yor{\`u}b{\'a} QA dataset derived from Nigerian drug labels, comprising 460 question{--}answer pairs across 92 drugs, which was used to evaluate the impact of different retrieval strategies: hybrid lexical{--}semantic retrieval, Hypothetical Document Embeddings(HyDE), and Cross-Encoder re-ranking. Our results show that hybrid retrieval strategies, combining lexical and semantic signals, generally yield more reliable and clinically accurate responses, while other advanced re-ranking approaches show inconsistent improvements. These findings hereby underscore the importance of effective retrieval design for safe and trustworthy multilingual healthcare QA systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tairu-adebesin-2026-evaluating">
<titleInfo>
<title>Evaluating Retrieval-Augmented Generation for Medication Question Answering on Nigerian Drug Labels in Yorùbá</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zainab</namePart>
<namePart type="family">Tairu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aramide</namePart>
<namePart type="family">Adebesin</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 Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</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">979-8-89176-377-7</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have the potential to improve healthcare information access in Nigeria, but they risk generating unsafe or inaccurate responses when used in low-resource languages such as Yorùbá. Retrieval-Augmented Generation (RAG) has since emerged as a promising approach to mitigate hallucinations by grounding LLM outputs in verified knowledge sources. To assess its effectiveness in low-resource contexts, we construct a controlled Yorùbá QA dataset derived from Nigerian drug labels, comprising 460 question–answer pairs across 92 drugs, which was used to evaluate the impact of different retrieval strategies: hybrid lexical–semantic retrieval, Hypothetical Document Embeddings(HyDE), and Cross-Encoder re-ranking. Our results show that hybrid retrieval strategies, combining lexical and semantic signals, generally yield more reliable and clinically accurate responses, while other advanced re-ranking approaches show inconsistent improvements. These findings hereby underscore the importance of effective retrieval design for safe and trustworthy multilingual healthcare QA systems.</abstract>
<identifier type="citekey">tairu-adebesin-2026-evaluating</identifier>
<location>
<url>https://aclanthology.org/2026.loreslm-1.8/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>90</start>
<end>97</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Retrieval-Augmented Generation for Medication Question Answering on Nigerian Drug Labels in Yorùbá
%A Tairu, Zainab
%A Adebesin, Aramide
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Plum, Alistair
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-377-7
%F tairu-adebesin-2026-evaluating
%X Large Language Models (LLMs) have the potential to improve healthcare information access in Nigeria, but they risk generating unsafe or inaccurate responses when used in low-resource languages such as Yorùbá. Retrieval-Augmented Generation (RAG) has since emerged as a promising approach to mitigate hallucinations by grounding LLM outputs in verified knowledge sources. To assess its effectiveness in low-resource contexts, we construct a controlled Yorùbá QA dataset derived from Nigerian drug labels, comprising 460 question–answer pairs across 92 drugs, which was used to evaluate the impact of different retrieval strategies: hybrid lexical–semantic retrieval, Hypothetical Document Embeddings(HyDE), and Cross-Encoder re-ranking. Our results show that hybrid retrieval strategies, combining lexical and semantic signals, generally yield more reliable and clinically accurate responses, while other advanced re-ranking approaches show inconsistent improvements. These findings hereby underscore the importance of effective retrieval design for safe and trustworthy multilingual healthcare QA systems.
%U https://aclanthology.org/2026.loreslm-1.8/
%P 90-97
Markdown (Informal)
[Evaluating Retrieval-Augmented Generation for Medication Question Answering on Nigerian Drug Labels in Yorùbá](https://aclanthology.org/2026.loreslm-1.8/) (Tairu & Adebesin, LoResLM 2026)
ACL