@inproceedings{el-fatimi-etal-2026-trumediqa,
title = "{TRUMEDIQA}: A Modular Trustworthy {RAG} Pipeline for Multilingual Medical Question Answering",
author = "El Fatimi, Meryem and
Nainia, Ayoub and
Zahir, Jihad",
editor = "Ben Abacha, Asma and
Bethard, Steven and
Bitterman, Danielle and
Naumann, Tristan and
Roberts, Kirk",
booktitle = "Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical {NLP}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.clinicalnlp-1.6/",
doi = "10.63317/4emkg4hncbzi",
pages = "49--56",
abstract = {Medical question answering systems must balance usefulness with safety, particularly in low-resource linguistic settings where robustness is limited and hallucinations can cause harm. We present TRUMEDIQA, a reproducible multilingual medical QA pipeline for Moroccan Darija, Arabic, French, and English, deployed on WhatsApp with text and voice interactions. TRUMEDIQA uses layered decision-making: (i) language identification, (ii) a pre-retrieval intent router that maps queries to one of 38 clinical FAQ categories to constrain retrieval, and (iii) post-retrieval LLM-based re-ranking that selects the best candidate answer or returns a null decision to trigger a safe fallback (abstention). Answers are retrieved from a curated FAQ knowledge base validated by medical professionals. We evaluate TRUMEDIQA with 21 participants submitting 290 questions across four languages. An expert annotator labels each interaction as relevant, acceptable, or irrelevant, and we also measure correct abstentions when no suitable answer exists in the knowledge base. An ablation study shows that routing and re-ranking improve the weighted relevance score from 0.25 to 0.94 and precision from 0.53 to 0.98 versus a na{\"i}ve retrieval baseline, while increasing correct abstention on unanswerable queries from 4.38{\%} to 69.77{\%}.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-fatimi-etal-2026-trumediqa">
<titleInfo>
<title>TRUMEDIQA: A Modular Trustworthy RAG Pipeline for Multilingual Medical Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meryem</namePart>
<namePart type="family">El Fatimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayoub</namePart>
<namePart type="family">Nainia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jihad</namePart>
<namePart type="family">Zahir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical question answering systems must balance usefulness with safety, particularly in low-resource linguistic settings where robustness is limited and hallucinations can cause harm. We present TRUMEDIQA, a reproducible multilingual medical QA pipeline for Moroccan Darija, Arabic, French, and English, deployed on WhatsApp with text and voice interactions. TRUMEDIQA uses layered decision-making: (i) language identification, (ii) a pre-retrieval intent router that maps queries to one of 38 clinical FAQ categories to constrain retrieval, and (iii) post-retrieval LLM-based re-ranking that selects the best candidate answer or returns a null decision to trigger a safe fallback (abstention). Answers are retrieved from a curated FAQ knowledge base validated by medical professionals. We evaluate TRUMEDIQA with 21 participants submitting 290 questions across four languages. An expert annotator labels each interaction as relevant, acceptable, or irrelevant, and we also measure correct abstentions when no suitable answer exists in the knowledge base. An ablation study shows that routing and re-ranking improve the weighted relevance score from 0.25 to 0.94 and precision from 0.53 to 0.98 versus a naïve retrieval baseline, while increasing correct abstention on unanswerable queries from 4.38% to 69.77%.</abstract>
<identifier type="citekey">el-fatimi-etal-2026-trumediqa</identifier>
<identifier type="doi">10.63317/4emkg4hncbzi</identifier>
<location>
<url>https://aclanthology.org/2026.clinicalnlp-1.6/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>49</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TRUMEDIQA: A Modular Trustworthy RAG Pipeline for Multilingual Medical Question Answering
%A El Fatimi, Meryem
%A Nainia, Ayoub
%A Zahir, Jihad
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Bitterman, Danielle
%Y Naumann, Tristan
%Y Roberts, Kirk
%S Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F el-fatimi-etal-2026-trumediqa
%X Medical question answering systems must balance usefulness with safety, particularly in low-resource linguistic settings where robustness is limited and hallucinations can cause harm. We present TRUMEDIQA, a reproducible multilingual medical QA pipeline for Moroccan Darija, Arabic, French, and English, deployed on WhatsApp with text and voice interactions. TRUMEDIQA uses layered decision-making: (i) language identification, (ii) a pre-retrieval intent router that maps queries to one of 38 clinical FAQ categories to constrain retrieval, and (iii) post-retrieval LLM-based re-ranking that selects the best candidate answer or returns a null decision to trigger a safe fallback (abstention). Answers are retrieved from a curated FAQ knowledge base validated by medical professionals. We evaluate TRUMEDIQA with 21 participants submitting 290 questions across four languages. An expert annotator labels each interaction as relevant, acceptable, or irrelevant, and we also measure correct abstentions when no suitable answer exists in the knowledge base. An ablation study shows that routing and re-ranking improve the weighted relevance score from 0.25 to 0.94 and precision from 0.53 to 0.98 versus a naïve retrieval baseline, while increasing correct abstention on unanswerable queries from 4.38% to 69.77%.
%R 10.63317/4emkg4hncbzi
%U https://aclanthology.org/2026.clinicalnlp-1.6/
%U https://doi.org/10.63317/4emkg4hncbzi
%P 49-56
Markdown (Informal)
[TRUMEDIQA: A Modular Trustworthy RAG Pipeline for Multilingual Medical Question Answering](https://aclanthology.org/2026.clinicalnlp-1.6/) (El Fatimi et al., ClinicalNLP 2026)
ACL