@inproceedings{soni-demner-fushman-2026-overview,
title = "Overview of the {A}rch{EHR}-{QA} 2026 Shared Task on Grounded Question Answering from Electronic Health Records",
author = "Soni, Sarvesh and
Demner-Fushman, Dina",
editor = "Gupta, Deepak and
Thompson, Paul and
Ananiadou, Sophia and
Demner-Fushman, Dina",
booktitle = "Proceedings of the Third Workshop on Patient-Oriented Language Processing ({CL}4{H}ealth) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.cl4health-1.23/",
doi = "10.63317/3nmxw7vuu7mn",
pages = "255--267",
abstract = "We present an overview of the ArchEHR-QA 2026 Shared Task on grounded question answering from electronic health records (EHRs), organized at the CL4Health Workshop at LREC 2026. The 2026 task decomposes grounded EHR question answering (QA) into four complementary subtasks: question interpretation, evidence identification, answer generation, and evidence alignment. We evaluated submitted systems for the text-generation subtasks (question interpretation and answer generation) using lexical, semantic, and grounding-sensitive automatic metrics, and for the evidence-centric subtasks (evidence identification and evidence alignment) using precision, recall, and F1. The shared task received 198 submitted runs from 43 teams, and 17 teams additionally provided system descriptions for this overview. The highest-ranked systems differed across subtasks, and gains over the organizer baseline were largest on the evidence-centric subtasks. Across submitted system descriptions, prompt-based large language model (LLM) pipelines were dominant, whereas task-specific fine-tuning was rare; retrieval, self-consistency, and ensembling were especially common in the strongest evidence-centric systems. In this paper, we describe the task design, data, evaluation protocol, baselines, participation, official results, and common system characteristics, and discuss implications for developing clinically faithful and transparent QA systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="soni-demner-fushman-2026-overview">
<titleInfo>
<title>Overview of the ArchEHR-QA 2026 Shared Task on Grounded Question Answering from Electronic Health Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarvesh</namePart>
<namePart type="family">Soni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</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 Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</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>We present an overview of the ArchEHR-QA 2026 Shared Task on grounded question answering from electronic health records (EHRs), organized at the CL4Health Workshop at LREC 2026. The 2026 task decomposes grounded EHR question answering (QA) into four complementary subtasks: question interpretation, evidence identification, answer generation, and evidence alignment. We evaluated submitted systems for the text-generation subtasks (question interpretation and answer generation) using lexical, semantic, and grounding-sensitive automatic metrics, and for the evidence-centric subtasks (evidence identification and evidence alignment) using precision, recall, and F1. The shared task received 198 submitted runs from 43 teams, and 17 teams additionally provided system descriptions for this overview. The highest-ranked systems differed across subtasks, and gains over the organizer baseline were largest on the evidence-centric subtasks. Across submitted system descriptions, prompt-based large language model (LLM) pipelines were dominant, whereas task-specific fine-tuning was rare; retrieval, self-consistency, and ensembling were especially common in the strongest evidence-centric systems. In this paper, we describe the task design, data, evaluation protocol, baselines, participation, official results, and common system characteristics, and discuss implications for developing clinically faithful and transparent QA systems.</abstract>
<identifier type="citekey">soni-demner-fushman-2026-overview</identifier>
<identifier type="doi">10.63317/3nmxw7vuu7mn</identifier>
<location>
<url>https://aclanthology.org/2026.cl4health-1.23/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>255</start>
<end>267</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overview of the ArchEHR-QA 2026 Shared Task on Grounded Question Answering from Electronic Health Records
%A Soni, Sarvesh
%A Demner-Fushman, Dina
%Y Gupta, Deepak
%Y Thompson, Paul
%Y Ananiadou, Sophia
%Y Demner-Fushman, Dina
%S Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F soni-demner-fushman-2026-overview
%X We present an overview of the ArchEHR-QA 2026 Shared Task on grounded question answering from electronic health records (EHRs), organized at the CL4Health Workshop at LREC 2026. The 2026 task decomposes grounded EHR question answering (QA) into four complementary subtasks: question interpretation, evidence identification, answer generation, and evidence alignment. We evaluated submitted systems for the text-generation subtasks (question interpretation and answer generation) using lexical, semantic, and grounding-sensitive automatic metrics, and for the evidence-centric subtasks (evidence identification and evidence alignment) using precision, recall, and F1. The shared task received 198 submitted runs from 43 teams, and 17 teams additionally provided system descriptions for this overview. The highest-ranked systems differed across subtasks, and gains over the organizer baseline were largest on the evidence-centric subtasks. Across submitted system descriptions, prompt-based large language model (LLM) pipelines were dominant, whereas task-specific fine-tuning was rare; retrieval, self-consistency, and ensembling were especially common in the strongest evidence-centric systems. In this paper, we describe the task design, data, evaluation protocol, baselines, participation, official results, and common system characteristics, and discuss implications for developing clinically faithful and transparent QA systems.
%R 10.63317/3nmxw7vuu7mn
%U https://aclanthology.org/2026.cl4health-1.23/
%U https://doi.org/10.63317/3nmxw7vuu7mn
%P 255-267
Markdown (Informal)
[Overview of the ArchEHR-QA 2026 Shared Task on Grounded Question Answering from Electronic Health Records](https://aclanthology.org/2026.cl4health-1.23/) (Soni & Demner-Fushman, CL4Health 2026)
ACL