@inproceedings{petrucco-etal-2026-alyas,
title = "Alyas: Evidence-Grounded Synthetic Populations for Simulated Social and Market Research",
author = "Petrucco, Luigi and
Bortolin, Samuel and
Leonelli, Elena and
Suardi, Eric and
Zorzi, Elena and
Miorandi, Daniele and
Piazza, Davide",
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.30/",
pages = "302--309",
ISBN = "979-8-89176-461-3",
abstract = "Large language models are increasingly used in social-science and market research to stand in for human respondents, exploring questions ahead of fieldwork or piloting instruments. Existing systems address one facet at a time (a population{'}s demographics, an individual{'}s profile, or an answer distribution elicited from a single prompt), and few serve users without social-science training. We present Alyas, a research-simulation platform in which an agentic methodologist assistant guides the user from a research goal to a study design, laid out as a branching graph of research artifacts, and simulates its field phase over a synthetic population grounded in institutional statistical sources. On held-out Italian and US microdata, the generated populations reconstruct demographic structure the engine was not given, and, on the Italian microdata, profile-conditioned respondents answer close to the real subgroups they simulate."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petrucco-etal-2026-alyas">
<titleInfo>
<title>Alyas: Evidence-Grounded Synthetic Populations for Simulated Social and Market Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luigi</namePart>
<namePart type="family">Petrucco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Bortolin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Leonelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Suardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Zorzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniele</namePart>
<namePart type="family">Miorandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Piazza</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>Large language models are increasingly used in social-science and market research to stand in for human respondents, exploring questions ahead of fieldwork or piloting instruments. Existing systems address one facet at a time (a population’s demographics, an individual’s profile, or an answer distribution elicited from a single prompt), and few serve users without social-science training. We present Alyas, a research-simulation platform in which an agentic methodologist assistant guides the user from a research goal to a study design, laid out as a branching graph of research artifacts, and simulates its field phase over a synthetic population grounded in institutional statistical sources. On held-out Italian and US microdata, the generated populations reconstruct demographic structure the engine was not given, and, on the Italian microdata, profile-conditioned respondents answer close to the real subgroups they simulate.</abstract>
<identifier type="citekey">petrucco-etal-2026-alyas</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-demos.30/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>302</start>
<end>309</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Alyas: Evidence-Grounded Synthetic Populations for Simulated Social and Market Research
%A Petrucco, Luigi
%A Bortolin, Samuel
%A Leonelli, Elena
%A Suardi, Eric
%A Zorzi, Elena
%A Miorandi, Daniele
%A Piazza, Davide
%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 petrucco-etal-2026-alyas
%X Large language models are increasingly used in social-science and market research to stand in for human respondents, exploring questions ahead of fieldwork or piloting instruments. Existing systems address one facet at a time (a population’s demographics, an individual’s profile, or an answer distribution elicited from a single prompt), and few serve users without social-science training. We present Alyas, a research-simulation platform in which an agentic methodologist assistant guides the user from a research goal to a study design, laid out as a branching graph of research artifacts, and simulates its field phase over a synthetic population grounded in institutional statistical sources. On held-out Italian and US microdata, the generated populations reconstruct demographic structure the engine was not given, and, on the Italian microdata, profile-conditioned respondents answer close to the real subgroups they simulate.
%U https://aclanthology.org/2026.emnlp-demos.30/
%P 302-309
Markdown (Informal)
[Alyas: Evidence-Grounded Synthetic Populations for Simulated Social and Market Research](https://aclanthology.org/2026.emnlp-demos.30/) (Petrucco et al., EMNLP 2026)
ACL