@inproceedings{zhong-etal-2025-pluralistic,
title = "Pluralistic Alignment for Healthcare: A Role-Driven Framework",
author = "Zhong, Jiayou and
Shetty, Anudeex and
Jia, Chao and
Lin, Xuanrui and
Naseem, Usman",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1596/",
doi = "10.18653/v1/2025.emnlp-main.1596",
pages = "31320--31343",
ISBN = "979-8-89176-332-6",
abstract = "As large language models are increasingly deployed in sensitive domains such as healthcare, ensuring their outputs reflect the diverse values and perspectives held across populations is critical. However, existing alignment approaches, including pluralistic paradigms like Modular Pluralism, often fall short in the health domain, where personal, cultural, and situational factors shape pluralism. Motivated by the aforementioned healthcare challenges, we propose a first lightweight, generalizable, pluralistic alignment approach, ETHOSAGENTS, designed to simulate diverse perspectives and values. We empirically show that it advances the pluralistic alignment for all three modes across seven varying-sized open and closed models. Our findings reveal that health-related pluralism demands adaptable and normatively aware approaches, offering insights into how these models can better respect diversity in other high-stakes domains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhong-etal-2025-pluralistic">
<titleInfo>
<title>Pluralistic Alignment for Healthcare: A Role-Driven Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiayou</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anudeex</namePart>
<namePart type="family">Shetty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanrui</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Usman</namePart>
<namePart type="family">Naseem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>As large language models are increasingly deployed in sensitive domains such as healthcare, ensuring their outputs reflect the diverse values and perspectives held across populations is critical. However, existing alignment approaches, including pluralistic paradigms like Modular Pluralism, often fall short in the health domain, where personal, cultural, and situational factors shape pluralism. Motivated by the aforementioned healthcare challenges, we propose a first lightweight, generalizable, pluralistic alignment approach, ETHOSAGENTS, designed to simulate diverse perspectives and values. We empirically show that it advances the pluralistic alignment for all three modes across seven varying-sized open and closed models. Our findings reveal that health-related pluralism demands adaptable and normatively aware approaches, offering insights into how these models can better respect diversity in other high-stakes domains.</abstract>
<identifier type="citekey">zhong-etal-2025-pluralistic</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.1596</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1596/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>31320</start>
<end>31343</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pluralistic Alignment for Healthcare: A Role-Driven Framework
%A Zhong, Jiayou
%A Shetty, Anudeex
%A Jia, Chao
%A Lin, Xuanrui
%A Naseem, Usman
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F zhong-etal-2025-pluralistic
%X As large language models are increasingly deployed in sensitive domains such as healthcare, ensuring their outputs reflect the diverse values and perspectives held across populations is critical. However, existing alignment approaches, including pluralistic paradigms like Modular Pluralism, often fall short in the health domain, where personal, cultural, and situational factors shape pluralism. Motivated by the aforementioned healthcare challenges, we propose a first lightweight, generalizable, pluralistic alignment approach, ETHOSAGENTS, designed to simulate diverse perspectives and values. We empirically show that it advances the pluralistic alignment for all three modes across seven varying-sized open and closed models. Our findings reveal that health-related pluralism demands adaptable and normatively aware approaches, offering insights into how these models can better respect diversity in other high-stakes domains.
%R 10.18653/v1/2025.emnlp-main.1596
%U https://aclanthology.org/2025.emnlp-main.1596/
%U https://doi.org/10.18653/v1/2025.emnlp-main.1596
%P 31320-31343
Markdown (Informal)
[Pluralistic Alignment for Healthcare: A Role-Driven Framework](https://aclanthology.org/2025.emnlp-main.1596/) (Zhong et al., EMNLP 2025)
ACL
- Jiayou Zhong, Anudeex Shetty, Chao Jia, Xuanrui Lin, and Usman Naseem. 2025. Pluralistic Alignment for Healthcare: A Role-Driven Framework. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 31320–31343, Suzhou, China. Association for Computational Linguistics.