@inproceedings{ferrazzi-etal-2026-multilingual,
title = "Multilingual Medical Reasoning for Question Answering with Large Language Models",
author = "Ferrazzi, Pietro and
Soroa, Aitor and
Agerri, Rodrigo",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1105/",
pages = "23365--23387",
ISBN = "979-8-89176-462-0",
abstract = "Large Language Models with reasoning capabilities have recently shown strong promise for medical Question Answering. Current approaches report competitive results on English benchmarks through knowledge distillation from large models, yet multilingual coverage remains limited. We extend this line of research by presenting a method to generate multilingual reasoning traces that enrich the distillation paradigm with factual information from Wikipedia. Using a retrieval-augmented generation pipeline over WikiProject Medicine, we produce 500k reasoning traces in English, Italian, and Spanish. The traces are generated to solve medical questions drawn from MedQA and MedMCQA, both of which we extend to Italian and Spanish. We evaluate our approach across in-domain and out-of-domain Medical QA benchmarks, demonstrating consistent performance gains in both few-shot in-context learning and supervised fine-tuning settings, achieving state-of-the-art results among 8B-parameter models across multiple model families. With the aim of fostering the development of multilingual clinical decision-support tools, we release the complete suite of resources: reasoning traces, translated datasets, Medical Wikipedia, and fine-tuned models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ferrazzi-etal-2026-multilingual">
<titleInfo>
<title>Multilingual Medical Reasoning for Question Answering with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pietro</namePart>
<namePart type="family">Ferrazzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitor</namePart>
<namePart type="family">Soroa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Agerri</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Large Language Models with reasoning capabilities have recently shown strong promise for medical Question Answering. Current approaches report competitive results on English benchmarks through knowledge distillation from large models, yet multilingual coverage remains limited. We extend this line of research by presenting a method to generate multilingual reasoning traces that enrich the distillation paradigm with factual information from Wikipedia. Using a retrieval-augmented generation pipeline over WikiProject Medicine, we produce 500k reasoning traces in English, Italian, and Spanish. The traces are generated to solve medical questions drawn from MedQA and MedMCQA, both of which we extend to Italian and Spanish. We evaluate our approach across in-domain and out-of-domain Medical QA benchmarks, demonstrating consistent performance gains in both few-shot in-context learning and supervised fine-tuning settings, achieving state-of-the-art results among 8B-parameter models across multiple model families. With the aim of fostering the development of multilingual clinical decision-support tools, we release the complete suite of resources: reasoning traces, translated datasets, Medical Wikipedia, and fine-tuned models.</abstract>
<identifier type="citekey">ferrazzi-etal-2026-multilingual</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1105/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>23365</start>
<end>23387</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Medical Reasoning for Question Answering with Large Language Models
%A Ferrazzi, Pietro
%A Soroa, Aitor
%A Agerri, Rodrigo
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F ferrazzi-etal-2026-multilingual
%X Large Language Models with reasoning capabilities have recently shown strong promise for medical Question Answering. Current approaches report competitive results on English benchmarks through knowledge distillation from large models, yet multilingual coverage remains limited. We extend this line of research by presenting a method to generate multilingual reasoning traces that enrich the distillation paradigm with factual information from Wikipedia. Using a retrieval-augmented generation pipeline over WikiProject Medicine, we produce 500k reasoning traces in English, Italian, and Spanish. The traces are generated to solve medical questions drawn from MedQA and MedMCQA, both of which we extend to Italian and Spanish. We evaluate our approach across in-domain and out-of-domain Medical QA benchmarks, demonstrating consistent performance gains in both few-shot in-context learning and supervised fine-tuning settings, achieving state-of-the-art results among 8B-parameter models across multiple model families. With the aim of fostering the development of multilingual clinical decision-support tools, we release the complete suite of resources: reasoning traces, translated datasets, Medical Wikipedia, and fine-tuned models.
%U https://aclanthology.org/2026.findings-emnlp.1105/
%P 23365-23387
Markdown (Informal)
[Multilingual Medical Reasoning for Question Answering with Large Language Models](https://aclanthology.org/2026.findings-emnlp.1105/) (Ferrazzi et al., Findings 2026)
ACL