@inproceedings{nhu-etal-2026-claas,
title = "{CLAAS}: Conditional {LVLM}-enabled Attribute-Aware response Simulation for Public Health Education",
author = "Nhu, Anh N and
Yang, Jenna and
Zheng, Laura Yu and
Touche-Howard, Sylvette La and
Zeeger, Tracy M. and
Lin, Ming",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2007/",
pages = "45706--45746",
ISBN = "979-8-89176-459-0",
abstract = "Modeling how diverse communities respond to public health messages is critical for training students to design targeted communication materials. However, no method is currently available to iteratively evaluate how different populations may perceive their campaign designs before human-subject testing. Despite progress in VLM/LLM-based psychometric simulation, community simulators for public health education remain largely unexplored. We reframe VLMs as attribute-aware community response simulators and introduce CLAAS, to our knowledge the first multimodal response simulation tool for public-health higher education. CLAAS aligns open-source VLMs, such as Gemma3, Llama-3.2, and Qwen2.5-VL, with an in-house survey dataset of 33K+ responses from 1K+ participants to simulate trait-conditioned emotional, behavioral, and sentimental responses. Quantitatively, attribute-aligned VLMs consistently outperform zero-shot and random baselines and generalize to unseen communication strategies. Beyond dataset evaluation, our pilot studies in real course sessions across two semesters demonstrate CLAAS{'}s potential practical relevance in educational settings. Most students reported CLAAS provided useful feedback and generated responses aligned with their expectations. This study suggests attribute-aware VLM support experiential public health education and promote a socially impactful research direction: interactive population simulator for community-centered communication design."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nhu-etal-2026-claas">
<titleInfo>
<title>CLAAS: Conditional LVLM-enabled Attribute-Aware response Simulation for Public Health Education</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Nhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jenna</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="given">Yu</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylvette</namePart>
<namePart type="given">La</namePart>
<namePart type="family">Touche-Howard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tracy</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Zeeger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Lin</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Modeling how diverse communities respond to public health messages is critical for training students to design targeted communication materials. However, no method is currently available to iteratively evaluate how different populations may perceive their campaign designs before human-subject testing. Despite progress in VLM/LLM-based psychometric simulation, community simulators for public health education remain largely unexplored. We reframe VLMs as attribute-aware community response simulators and introduce CLAAS, to our knowledge the first multimodal response simulation tool for public-health higher education. CLAAS aligns open-source VLMs, such as Gemma3, Llama-3.2, and Qwen2.5-VL, with an in-house survey dataset of 33K+ responses from 1K+ participants to simulate trait-conditioned emotional, behavioral, and sentimental responses. Quantitatively, attribute-aligned VLMs consistently outperform zero-shot and random baselines and generalize to unseen communication strategies. Beyond dataset evaluation, our pilot studies in real course sessions across two semesters demonstrate CLAAS’s potential practical relevance in educational settings. Most students reported CLAAS provided useful feedback and generated responses aligned with their expectations. This study suggests attribute-aware VLM support experiential public health education and promote a socially impactful research direction: interactive population simulator for community-centered communication design.</abstract>
<identifier type="citekey">nhu-etal-2026-claas</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2007/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>45706</start>
<end>45746</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLAAS: Conditional LVLM-enabled Attribute-Aware response Simulation for Public Health Education
%A Nhu, Anh N.
%A Yang, Jenna
%A Zheng, Laura Yu
%A Touche-Howard, Sylvette La
%A Zeeger, Tracy M.
%A Lin, Ming
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F nhu-etal-2026-claas
%X Modeling how diverse communities respond to public health messages is critical for training students to design targeted communication materials. However, no method is currently available to iteratively evaluate how different populations may perceive their campaign designs before human-subject testing. Despite progress in VLM/LLM-based psychometric simulation, community simulators for public health education remain largely unexplored. We reframe VLMs as attribute-aware community response simulators and introduce CLAAS, to our knowledge the first multimodal response simulation tool for public-health higher education. CLAAS aligns open-source VLMs, such as Gemma3, Llama-3.2, and Qwen2.5-VL, with an in-house survey dataset of 33K+ responses from 1K+ participants to simulate trait-conditioned emotional, behavioral, and sentimental responses. Quantitatively, attribute-aligned VLMs consistently outperform zero-shot and random baselines and generalize to unseen communication strategies. Beyond dataset evaluation, our pilot studies in real course sessions across two semesters demonstrate CLAAS’s potential practical relevance in educational settings. Most students reported CLAAS provided useful feedback and generated responses aligned with their expectations. This study suggests attribute-aware VLM support experiential public health education and promote a socially impactful research direction: interactive population simulator for community-centered communication design.
%U https://aclanthology.org/2026.emnlp-main.2007/
%P 45706-45746
Markdown (Informal)
[CLAAS: Conditional LVLM-enabled Attribute-Aware response Simulation for Public Health Education](https://aclanthology.org/2026.emnlp-main.2007/) (Nhu et al., EMNLP 2026)
ACL