@inproceedings{buns-etal-2026-wispermed,
title = "{W}is{P}er{M}ed at {A}rch{EHR}-{QA} 2026: Retrieval-Augmented Prompting for Grounded {EHR} Question Answering",
author = {B{\"u}ns, Jan-Henning and
Pakull, Tabea Margareta Grace and
Damm, Hendrik and
Chu, Bohao and
Friedrich, Christoph M. and
Nensa, Felix and
Livingstone, Elisabeth and
Horn, Peter A. and
Fuhr, Norbert},
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-1.42/",
doi = "10.63317/5bb4gnhkbqjq",
pages = "455--468",
abstract = "ArchEHR-QA is a grounded question-answering (QA) task for electronic health records (EHRs) comprising four subtasks: (1) question rewriting, (2) evidence identification, (3) grounded answer generation, and (4) answer-evidence alignment. In this work, we present a modular pipeline centered on retrieval-augmented generation (RAG). For Subtask 1, RAG few-shot prompting outperformed both PEFT and prompt-only baselines on the development set; however, Claude few-shot proved substantially more robust on the test set, ranking 6th out of 13 participating teams (score: 26.94). For Subtask 2, a union ensemble of open-weight LLMs (GPT-OSS-120B and Qwen3-30B-A3B) achieved a 56.7 micro-F1, rivaling the proprietary Claude Opus 4.6 while demonstrating higher recall (53.6). For Subtask 3, our RAG few-shot approach using Claude Opus 4.5 achieved the 1st place out of 13 participating teams (score: 36.33). Finally, for Subtask 4, a zero-shot Claude Opus 4.6 configuration ranked 2nd out of 16 participating teams (score: 81.3)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="buns-etal-2026-wispermed">
<titleInfo>
<title>WisPerMed at ArchEHR-QA 2026: Retrieval-Augmented Prompting for Grounded EHR Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan-Henning</namePart>
<namePart type="family">Büns</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tabea</namePart>
<namePart type="given">Margareta</namePart>
<namePart type="given">Grace</namePart>
<namePart type="family">Pakull</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hendrik</namePart>
<namePart type="family">Damm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bohao</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Nensa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisabeth</namePart>
<namePart type="family">Livingstone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Horn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Norbert</namePart>
<namePart type="family">Fuhr</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>ArchEHR-QA is a grounded question-answering (QA) task for electronic health records (EHRs) comprising four subtasks: (1) question rewriting, (2) evidence identification, (3) grounded answer generation, and (4) answer-evidence alignment. In this work, we present a modular pipeline centered on retrieval-augmented generation (RAG). For Subtask 1, RAG few-shot prompting outperformed both PEFT and prompt-only baselines on the development set; however, Claude few-shot proved substantially more robust on the test set, ranking 6th out of 13 participating teams (score: 26.94). For Subtask 2, a union ensemble of open-weight LLMs (GPT-OSS-120B and Qwen3-30B-A3B) achieved a 56.7 micro-F1, rivaling the proprietary Claude Opus 4.6 while demonstrating higher recall (53.6). For Subtask 3, our RAG few-shot approach using Claude Opus 4.5 achieved the 1st place out of 13 participating teams (score: 36.33). Finally, for Subtask 4, a zero-shot Claude Opus 4.6 configuration ranked 2nd out of 16 participating teams (score: 81.3).</abstract>
<identifier type="citekey">buns-etal-2026-wispermed</identifier>
<identifier type="doi">10.63317/5bb4gnhkbqjq</identifier>
<location>
<url>https://aclanthology.org/2026.cl4health-1.42/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>455</start>
<end>468</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WisPerMed at ArchEHR-QA 2026: Retrieval-Augmented Prompting for Grounded EHR Question Answering
%A Büns, Jan-Henning
%A Pakull, Tabea Margareta Grace
%A Damm, Hendrik
%A Chu, Bohao
%A Friedrich, Christoph M.
%A Nensa, Felix
%A Livingstone, Elisabeth
%A Horn, Peter A.
%A Fuhr, Norbert
%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 buns-etal-2026-wispermed
%X ArchEHR-QA is a grounded question-answering (QA) task for electronic health records (EHRs) comprising four subtasks: (1) question rewriting, (2) evidence identification, (3) grounded answer generation, and (4) answer-evidence alignment. In this work, we present a modular pipeline centered on retrieval-augmented generation (RAG). For Subtask 1, RAG few-shot prompting outperformed both PEFT and prompt-only baselines on the development set; however, Claude few-shot proved substantially more robust on the test set, ranking 6th out of 13 participating teams (score: 26.94). For Subtask 2, a union ensemble of open-weight LLMs (GPT-OSS-120B and Qwen3-30B-A3B) achieved a 56.7 micro-F1, rivaling the proprietary Claude Opus 4.6 while demonstrating higher recall (53.6). For Subtask 3, our RAG few-shot approach using Claude Opus 4.5 achieved the 1st place out of 13 participating teams (score: 36.33). Finally, for Subtask 4, a zero-shot Claude Opus 4.6 configuration ranked 2nd out of 16 participating teams (score: 81.3).
%R 10.63317/5bb4gnhkbqjq
%U https://aclanthology.org/2026.cl4health-1.42/
%U https://doi.org/10.63317/5bb4gnhkbqjq
%P 455-468
Markdown (Informal)
[WisPerMed at ArchEHR-QA 2026: Retrieval-Augmented Prompting for Grounded EHR Question Answering](https://aclanthology.org/2026.cl4health-1.42/) (Büns et al., CL4Health 2026)
ACL
- Jan-Henning Büns, Tabea Margareta Grace Pakull, Hendrik Damm, Bohao Chu, Christoph M. Friedrich, Felix Nensa, Elisabeth Livingstone, Peter A. Horn, and Norbert Fuhr. 2026. WisPerMed at ArchEHR-QA 2026: Retrieval-Augmented Prompting for Grounded EHR Question Answering. In Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026, pages 455–468, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).