@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://preview.aclanthology.org/manual-author-scripts/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."
}