@inproceedings{izhar-etal-2026-measuring,
title = "Measuring Cultural Alignment Beyond the Average: A Framework for Evaluating Maternal-Health {LLM} Interactions in {I}ndian Contexts",
author = "Izhar, Umaira and
Arora, Gunjan and
Singh, Pushpendra",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1355/",
pages = "28759--28778",
ISBN = "979-8-89176-462-0",
abstract = "Existing evaluation methods for healthcare LLMs primarily assess factual correctness, safety, and fluency, while providing limited insight into whether generated interactions reflect culturally situated healthcare reasoning. This limitation is particularly important in maternal health, where care decisions are shaped by social and relational norms. We introduce MH-INDIC, a culturally grounded evaluation framework for maternal-health interactions in Indian contexts that operationalises cultural behaviour through ten dimensions of maternal-health reasoning. Using a 26-item survey administered to 102 pregnant and postpartum women from urban and semi-urban North India, we evaluate ten LLMs under profile-conditioned prompting. Our evaluation separates aggregate cultural alignment and context-dependent sensitivity to demographic and household factors. While several proprietary models approximate human population-level distributions, all evaluated systems exhibit substantially reduced behavioural variation across profiles. We further show that human-grounded conditioning enhances the realism and contextual coherence of synthetic maternal health dialogues. Together, our findings highlight the importance of evaluating healthcare LLMs not only for factual correctness but also for their ability to model socially situated reasoning in culturally embedded healthcare settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="izhar-etal-2026-measuring">
<titleInfo>
<title>Measuring Cultural Alignment Beyond the Average: A Framework for Evaluating Maternal-Health LLM Interactions in Indian Contexts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Umaira</namePart>
<namePart type="family">Izhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gunjan</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpendra</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Existing evaluation methods for healthcare LLMs primarily assess factual correctness, safety, and fluency, while providing limited insight into whether generated interactions reflect culturally situated healthcare reasoning. This limitation is particularly important in maternal health, where care decisions are shaped by social and relational norms. We introduce MH-INDIC, a culturally grounded evaluation framework for maternal-health interactions in Indian contexts that operationalises cultural behaviour through ten dimensions of maternal-health reasoning. Using a 26-item survey administered to 102 pregnant and postpartum women from urban and semi-urban North India, we evaluate ten LLMs under profile-conditioned prompting. Our evaluation separates aggregate cultural alignment and context-dependent sensitivity to demographic and household factors. While several proprietary models approximate human population-level distributions, all evaluated systems exhibit substantially reduced behavioural variation across profiles. We further show that human-grounded conditioning enhances the realism and contextual coherence of synthetic maternal health dialogues. Together, our findings highlight the importance of evaluating healthcare LLMs not only for factual correctness but also for their ability to model socially situated reasoning in culturally embedded healthcare settings.</abstract>
<identifier type="citekey">izhar-etal-2026-measuring</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1355/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>28759</start>
<end>28778</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring Cultural Alignment Beyond the Average: A Framework for Evaluating Maternal-Health LLM Interactions in Indian Contexts
%A Izhar, Umaira
%A Arora, Gunjan
%A Singh, Pushpendra
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F izhar-etal-2026-measuring
%X Existing evaluation methods for healthcare LLMs primarily assess factual correctness, safety, and fluency, while providing limited insight into whether generated interactions reflect culturally situated healthcare reasoning. This limitation is particularly important in maternal health, where care decisions are shaped by social and relational norms. We introduce MH-INDIC, a culturally grounded evaluation framework for maternal-health interactions in Indian contexts that operationalises cultural behaviour through ten dimensions of maternal-health reasoning. Using a 26-item survey administered to 102 pregnant and postpartum women from urban and semi-urban North India, we evaluate ten LLMs under profile-conditioned prompting. Our evaluation separates aggregate cultural alignment and context-dependent sensitivity to demographic and household factors. While several proprietary models approximate human population-level distributions, all evaluated systems exhibit substantially reduced behavioural variation across profiles. We further show that human-grounded conditioning enhances the realism and contextual coherence of synthetic maternal health dialogues. Together, our findings highlight the importance of evaluating healthcare LLMs not only for factual correctness but also for their ability to model socially situated reasoning in culturally embedded healthcare settings.
%U https://aclanthology.org/2026.findings-emnlp.1355/
%P 28759-28778
Markdown (Informal)
[Measuring Cultural Alignment Beyond the Average: A Framework for Evaluating Maternal-Health LLM Interactions in Indian Contexts](https://aclanthology.org/2026.findings-emnlp.1355/) (Izhar et al., Findings 2026)
ACL