@inproceedings{zeinalipour-etal-2026-pharmaqa,
title = "{P}harma{QA}.{IT}: an {I}talian dataset for {Q}{\&}{A} in the pharmaceutical domain",
author = "Zeinalipour, Kamyar and
Zugarini, Andrea and
Zanollo, Asya and
Rigutini, Leonardo",
editor = {Matusevych, Yevgen and
Eryi{\u{g}}it, G{\"u}l{\c{s}}en and
Aletras, Nikolaos},
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Industry Track)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-industry.70/",
pages = "937--947",
ISBN = "979-8-89176-384-5",
abstract = "The growing use of Large Language Models (LLMs) for medical Question Answering (QA) requires reliable, evidence-grounded benchmarks beyond English. In Italy, Riassunti delle Caratteristiche del Prodotto (RCP) issued by the Italian Medicines Agency (AIFA) are the main regulatory source on medicines, yet no QA dataset exists on these documents, limiting the development and evaluation of trustworthy Italian QA systems.We introduce \textbf{PharmaQA.IT}, an Italian extractive QA dataset built from RCPs in PharmaER.IT. Using a semi-automatic pipeline, we (i) select informative pages from 1{,}077 leaflets, (ii) prompt a multimodal LLM on page images with professional personas to generate candidate question{--}answer pairs, and (iii) validate and normalise them with expert revision. The final dataset contains 861 high-quality question{--}answer pairs on indications, contraindications, dosage, warnings, interactions, and pharmacological properties.We frame PharmaQA.IT as an extractive QA benchmark with structured JSON outputs and evaluate a range of open and proprietary LLMs. Results show that open models approach closed-source performance under a chunking-and-retrieval setup. PharmaQA.IT, together with all code, prompts, and evaluation scripts, will be publicly released to support research on trustworthy Italian biomedical QA.PharmaQA.IT, together with all code, prompts, and evaluation scripts, is publicly available on Hugging Face to support research on trustworthy Italian biomedical QA."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeinalipour-etal-2026-pharmaqa">
<titleInfo>
<title>PharmaQA.IT: an Italian dataset for Q&A in the pharmaceutical domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kamyar</namePart>
<namePart type="family">Zeinalipour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Zugarini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asya</namePart>
<namePart type="family">Zanollo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Rigutini</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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yevgen</namePart>
<namePart type="family">Matusevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gülşen</namePart>
<namePart type="family">Eryiğit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</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">979-8-89176-384-5</identifier>
</relatedItem>
<abstract>The growing use of Large Language Models (LLMs) for medical Question Answering (QA) requires reliable, evidence-grounded benchmarks beyond English. In Italy, Riassunti delle Caratteristiche del Prodotto (RCP) issued by the Italian Medicines Agency (AIFA) are the main regulatory source on medicines, yet no QA dataset exists on these documents, limiting the development and evaluation of trustworthy Italian QA systems.We introduce PharmaQA.IT, an Italian extractive QA dataset built from RCPs in PharmaER.IT. Using a semi-automatic pipeline, we (i) select informative pages from 1,077 leaflets, (ii) prompt a multimodal LLM on page images with professional personas to generate candidate question–answer pairs, and (iii) validate and normalise them with expert revision. The final dataset contains 861 high-quality question–answer pairs on indications, contraindications, dosage, warnings, interactions, and pharmacological properties.We frame PharmaQA.IT as an extractive QA benchmark with structured JSON outputs and evaluate a range of open and proprietary LLMs. Results show that open models approach closed-source performance under a chunking-and-retrieval setup. PharmaQA.IT, together with all code, prompts, and evaluation scripts, will be publicly released to support research on trustworthy Italian biomedical QA.PharmaQA.IT, together with all code, prompts, and evaluation scripts, is publicly available on Hugging Face to support research on trustworthy Italian biomedical QA.</abstract>
<identifier type="citekey">zeinalipour-etal-2026-pharmaqa</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-industry.70/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>937</start>
<end>947</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PharmaQA.IT: an Italian dataset for Q&A in the pharmaceutical domain
%A Zeinalipour, Kamyar
%A Zugarini, Andrea
%A Zanollo, Asya
%A Rigutini, Leonardo
%Y Matusevych, Yevgen
%Y Eryiğit, Gülşen
%Y Aletras, Nikolaos
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-384-5
%F zeinalipour-etal-2026-pharmaqa
%X The growing use of Large Language Models (LLMs) for medical Question Answering (QA) requires reliable, evidence-grounded benchmarks beyond English. In Italy, Riassunti delle Caratteristiche del Prodotto (RCP) issued by the Italian Medicines Agency (AIFA) are the main regulatory source on medicines, yet no QA dataset exists on these documents, limiting the development and evaluation of trustworthy Italian QA systems.We introduce PharmaQA.IT, an Italian extractive QA dataset built from RCPs in PharmaER.IT. Using a semi-automatic pipeline, we (i) select informative pages from 1,077 leaflets, (ii) prompt a multimodal LLM on page images with professional personas to generate candidate question–answer pairs, and (iii) validate and normalise them with expert revision. The final dataset contains 861 high-quality question–answer pairs on indications, contraindications, dosage, warnings, interactions, and pharmacological properties.We frame PharmaQA.IT as an extractive QA benchmark with structured JSON outputs and evaluate a range of open and proprietary LLMs. Results show that open models approach closed-source performance under a chunking-and-retrieval setup. PharmaQA.IT, together with all code, prompts, and evaluation scripts, will be publicly released to support research on trustworthy Italian biomedical QA.PharmaQA.IT, together with all code, prompts, and evaluation scripts, is publicly available on Hugging Face to support research on trustworthy Italian biomedical QA.
%U https://aclanthology.org/2026.eacl-industry.70/
%P 937-947
Markdown (Informal)
[PharmaQA.IT: an Italian dataset for Q&A in the pharmaceutical domain](https://aclanthology.org/2026.eacl-industry.70/) (Zeinalipour et al., EACL 2026)
ACL
- Kamyar Zeinalipour, Andrea Zugarini, Asya Zanollo, and Leonardo Rigutini. 2026. PharmaQA.IT: an Italian dataset for Q&A in the pharmaceutical domain. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track), pages 937–947, Rabat, Morocco. Association for Computational Linguistics.