@inproceedings{park-etal-2026-response,
title = "Response Content Units: Evaluating Completeness and Proactiveness in Medical Open-Response Question Answering",
author = "Park, Yongsin and
Yim, Wen-wai and
McKibbin, Emma and
Ben Abacha, Asma and
Xia, Fei",
editor = "Mille, Simon and
Gehrmann, Sebastian and
Schmidtov{\'a}, Patr{\'i}cia and
Du{\v{s}}ek, Ond{\v{r}}ej and
Fadaee, Marzieh and
Lo, Kyle and
Santus, Enrico and
Stanovsky, Gabriel",
booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.gem-main.25/",
pages = "231--252",
ISBN = "979-8-89176-423-1",
abstract = "Remote clinical care has significantly increased the workload for healthcare professionals managing digital inquiries. While automated systems aim to alleviate this burden, consumer health questions present unique challenges due to their linguistic complexity and the need for proactive clinical guidance, which traditional question-answering models often overlook. We introduce the medical Response Content Units (RCU) schema, a framework that facilitates automatic analysis to identify question-answer completeness and critical answer subparts, which can then be used as tools for supporting clinician response or for automatic metric evaluation. Our analysis using this schema reveals a 16.4{\%} gap in response completeness in professional replies and demonstrates that essential medical directives are provided 2.4 to 12.1 times as frequently as direct answers. We provide baseline results and publicly release our annotations and source code to offer an evaluation framework that is more closely aligned with real-world clinical requirements."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2026-response">
<titleInfo>
<title>Response Content Units: Evaluating Completeness and Proactiveness in Medical Open-Response Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yongsin</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen-wai</namePart>
<namePart type="family">Yim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emma</namePart>
<namePart type="family">McKibbin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrícia</namePart>
<namePart type="family">Schmidtová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marzieh</namePart>
<namePart type="family">Fadaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-423-1</identifier>
</relatedItem>
<abstract>Remote clinical care has significantly increased the workload for healthcare professionals managing digital inquiries. While automated systems aim to alleviate this burden, consumer health questions present unique challenges due to their linguistic complexity and the need for proactive clinical guidance, which traditional question-answering models often overlook. We introduce the medical Response Content Units (RCU) schema, a framework that facilitates automatic analysis to identify question-answer completeness and critical answer subparts, which can then be used as tools for supporting clinician response or for automatic metric evaluation. Our analysis using this schema reveals a 16.4% gap in response completeness in professional replies and demonstrates that essential medical directives are provided 2.4 to 12.1 times as frequently as direct answers. We provide baseline results and publicly release our annotations and source code to offer an evaluation framework that is more closely aligned with real-world clinical requirements.</abstract>
<identifier type="citekey">park-etal-2026-response</identifier>
<location>
<url>https://aclanthology.org/2026.gem-main.25/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>231</start>
<end>252</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Response Content Units: Evaluating Completeness and Proactiveness in Medical Open-Response Question Answering
%A Park, Yongsin
%A Yim, Wen-wai
%A McKibbin, Emma
%A Ben Abacha, Asma
%A Xia, Fei
%Y Mille, Simon
%Y Gehrmann, Sebastian
%Y Schmidtová, Patrícia
%Y Dušek, Ondřej
%Y Fadaee, Marzieh
%Y Lo, Kyle
%Y Santus, Enrico
%Y Stanovsky, Gabriel
%S Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-423-1
%F park-etal-2026-response
%X Remote clinical care has significantly increased the workload for healthcare professionals managing digital inquiries. While automated systems aim to alleviate this burden, consumer health questions present unique challenges due to their linguistic complexity and the need for proactive clinical guidance, which traditional question-answering models often overlook. We introduce the medical Response Content Units (RCU) schema, a framework that facilitates automatic analysis to identify question-answer completeness and critical answer subparts, which can then be used as tools for supporting clinician response or for automatic metric evaluation. Our analysis using this schema reveals a 16.4% gap in response completeness in professional replies and demonstrates that essential medical directives are provided 2.4 to 12.1 times as frequently as direct answers. We provide baseline results and publicly release our annotations and source code to offer an evaluation framework that is more closely aligned with real-world clinical requirements.
%U https://aclanthology.org/2026.gem-main.25/
%P 231-252
Markdown (Informal)
[Response Content Units: Evaluating Completeness and Proactiveness in Medical Open-Response Question Answering](https://aclanthology.org/2026.gem-main.25/) (Park et al., GEM 2026)
ACL