Saved in:
Bibliographic Details
Main Authors: Humayun, Ameemah, Zubair, Bushra, Mustafa, Maryam
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.01907
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915594738073600
author Humayun, Ameemah
Zubair, Bushra
Mustafa, Maryam
author_facet Humayun, Ameemah
Zubair, Bushra
Mustafa, Maryam
contents Low-resource countries represent over 90% of maternal deaths, with Pakistan among the top four countries contributing nearly half in 2023. Since these deaths are mostly preventable, large language models (LLMs) can help address this crisis by automating health communication and risk assessment. However, sexual and reproductive health (SRH) communication in conservative contexts often relies on indirect language that obscures meaning, complicating LLM-based interventions. We conduct a two-stage study in Pakistan: (1) analyzing data from clinical observations, interviews, and focus groups with clinicians and patients, and (2) evaluating the interpretive capabilities of five popular LLMs on this data. Our analysis identifies two axes of communication (referential domain and expression approach) and shows LLMs struggle with semantic drift, myths, and polysemy in clinical interactions. We contribute: (1) empirical themes in SRH communication, (2) a categorization framework for indirect communication, (3) evaluation of LLM performance, and (4) design recommendations for culturally-situated SRH communication.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01907
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Between Myths and Metaphors: Rethinking LLMs for SRH in Conservative Contexts
Humayun, Ameemah
Zubair, Bushra
Mustafa, Maryam
Computers and Society
Artificial Intelligence
Human-Computer Interaction
Low-resource countries represent over 90% of maternal deaths, with Pakistan among the top four countries contributing nearly half in 2023. Since these deaths are mostly preventable, large language models (LLMs) can help address this crisis by automating health communication and risk assessment. However, sexual and reproductive health (SRH) communication in conservative contexts often relies on indirect language that obscures meaning, complicating LLM-based interventions. We conduct a two-stage study in Pakistan: (1) analyzing data from clinical observations, interviews, and focus groups with clinicians and patients, and (2) evaluating the interpretive capabilities of five popular LLMs on this data. Our analysis identifies two axes of communication (referential domain and expression approach) and shows LLMs struggle with semantic drift, myths, and polysemy in clinical interactions. We contribute: (1) empirical themes in SRH communication, (2) a categorization framework for indirect communication, (3) evaluation of LLM performance, and (4) design recommendations for culturally-situated SRH communication.
title Between Myths and Metaphors: Rethinking LLMs for SRH in Conservative Contexts
topic Computers and Society
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2511.01907