@inproceedings{yu-etal-2026-anamnesis,
title = "Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation",
author = "Yu, Song-Ze and
Suh, Joseph and
Chang, Serina and
Chan, David M.",
editor = "Agrawal, Sweta and
Abad, Alberto",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-demos.44/",
pages = "456--465",
ISBN = "979-8-89176-461-3",
abstract = "We present {\_}Anamnesis{\_}, an interactive system for demographically controllable survey simulation using large language models. Open-source and designed for {\_}non-technical{\_} users and researchers, Anamnesis enables the prototyping and stress-testing of survey instruments on virtual populations. The platform operationalizes the recently introduced Anthology and Alterity frameworks, which use structured narrative backstories to condition model responses, within a unified web interface. It supports open-ended generation, probabilistic demographic resampling, and multimodal (image and audio) surveys. We evaluate the system through two case studies: (1) replicating segments of Pew Research Center{'}s American Trends Panel (ATP) on political typology and biomedical issues and (2) emulating human preference in the New Yorker Caption Contest. In both cases, {\_}Anamnesis{\_} produces opinion distributions that more closely match real-world survey data than standard persona-prompting baselines, offering a transparent, reproducible, and open-source alternative to proprietary simulation services."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2026-anamnesis">
<titleInfo>
<title>Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Song-Ze</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Suh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serina</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Chan</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: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Abad</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">979-8-89176-461-3</identifier>
</relatedItem>
<abstract>We present _Anamnesis_, an interactive system for demographically controllable survey simulation using large language models. Open-source and designed for _non-technical_ users and researchers, Anamnesis enables the prototyping and stress-testing of survey instruments on virtual populations. The platform operationalizes the recently introduced Anthology and Alterity frameworks, which use structured narrative backstories to condition model responses, within a unified web interface. It supports open-ended generation, probabilistic demographic resampling, and multimodal (image and audio) surveys. We evaluate the system through two case studies: (1) replicating segments of Pew Research Center’s American Trends Panel (ATP) on political typology and biomedical issues and (2) emulating human preference in the New Yorker Caption Contest. In both cases, _Anamnesis_ produces opinion distributions that more closely match real-world survey data than standard persona-prompting baselines, offering a transparent, reproducible, and open-source alternative to proprietary simulation services.</abstract>
<identifier type="citekey">yu-etal-2026-anamnesis</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-demos.44/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>456</start>
<end>465</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation
%A Yu, Song-Ze
%A Suh, Joseph
%A Chang, Serina
%A Chan, David M.
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F yu-etal-2026-anamnesis
%X We present _Anamnesis_, an interactive system for demographically controllable survey simulation using large language models. Open-source and designed for _non-technical_ users and researchers, Anamnesis enables the prototyping and stress-testing of survey instruments on virtual populations. The platform operationalizes the recently introduced Anthology and Alterity frameworks, which use structured narrative backstories to condition model responses, within a unified web interface. It supports open-ended generation, probabilistic demographic resampling, and multimodal (image and audio) surveys. We evaluate the system through two case studies: (1) replicating segments of Pew Research Center’s American Trends Panel (ATP) on political typology and biomedical issues and (2) emulating human preference in the New Yorker Caption Contest. In both cases, _Anamnesis_ produces opinion distributions that more closely match real-world survey data than standard persona-prompting baselines, offering a transparent, reproducible, and open-source alternative to proprietary simulation services.
%U https://aclanthology.org/2026.emnlp-demos.44/
%P 456-465
Markdown (Informal)
[Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation](https://aclanthology.org/2026.emnlp-demos.44/) (Yu et al., EMNLP 2026)
ACL