@inproceedings{liu-etal-2026-beyond-individual,
title = "Beyond Individual Personas: Aligning Synthetic Dialogue to Population-Level Behavior Distributions",
author = "Liu, Xinyi and
Khaziev, Rinat and
Nayyeri, Hooshang and
Yilmaz, Emine and
Peris, Charith and
Thadakamalla, Hari P",
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.663/",
pages = "13903--13927",
ISBN = "979-8-89176-462-0",
abstract = "Synthetic dialogue corpora are increasingly used as proxies for target data, yet persona-grounded generators optimize individual conversations rather than corpus composition, yielding plausible dialogues with distorted population-level behavior mixes. We introduce GroupPersona, a framework that aligns synthetic corpora with a reference behavior distribution. GroupPersona turns population statistics into generation controls by discovering recurring behavioral groups in the reference corpus and using their prevalence and interaction patterns to condition user agents.\par We evaluate corpus-level fidelity through behavioral alignment and structural preservation, measured by average Jensen{--}Shannon distance over 12 behavior attributes and 5 dialogue structure attributes, respectively. Across four corpora spanning two source families and two construction regimes, GroupPersona reduces behavioral Jensen{--}Shannon distance from 0.234 to 0.177 over the best-average baseline, a 24.4{\%} reduction. It is best or tied-best on all four corpora. It maintains comparable structural distance at 0.167 versus 0.169. Together, these results show that GroupPersona improves population-level behavioral fidelity while preserving dialogue structure."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-beyond-individual">
<titleInfo>
<title>Beyond Individual Personas: Aligning Synthetic Dialogue to Population-Level Behavior Distributions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rinat</namePart>
<namePart type="family">Khaziev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hooshang</namePart>
<namePart type="family">Nayyeri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emine</namePart>
<namePart type="family">Yilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charith</namePart>
<namePart type="family">Peris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hari</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Thadakamalla</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>Synthetic dialogue corpora are increasingly used as proxies for target data, yet persona-grounded generators optimize individual conversations rather than corpus composition, yielding plausible dialogues with distorted population-level behavior mixes. We introduce GroupPersona, a framework that aligns synthetic corpora with a reference behavior distribution. GroupPersona turns population statistics into generation controls by discovering recurring behavioral groups in the reference corpus and using their prevalence and interaction patterns to condition user agents.\par We evaluate corpus-level fidelity through behavioral alignment and structural preservation, measured by average Jensen–Shannon distance over 12 behavior attributes and 5 dialogue structure attributes, respectively. Across four corpora spanning two source families and two construction regimes, GroupPersona reduces behavioral Jensen–Shannon distance from 0.234 to 0.177 over the best-average baseline, a 24.4% reduction. It is best or tied-best on all four corpora. It maintains comparable structural distance at 0.167 versus 0.169. Together, these results show that GroupPersona improves population-level behavioral fidelity while preserving dialogue structure.</abstract>
<identifier type="citekey">liu-etal-2026-beyond-individual</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.663/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>13903</start>
<end>13927</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Individual Personas: Aligning Synthetic Dialogue to Population-Level Behavior Distributions
%A Liu, Xinyi
%A Khaziev, Rinat
%A Nayyeri, Hooshang
%A Yilmaz, Emine
%A Peris, Charith
%A Thadakamalla, Hari P.
%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 liu-etal-2026-beyond-individual
%X Synthetic dialogue corpora are increasingly used as proxies for target data, yet persona-grounded generators optimize individual conversations rather than corpus composition, yielding plausible dialogues with distorted population-level behavior mixes. We introduce GroupPersona, a framework that aligns synthetic corpora with a reference behavior distribution. GroupPersona turns population statistics into generation controls by discovering recurring behavioral groups in the reference corpus and using their prevalence and interaction patterns to condition user agents.\par We evaluate corpus-level fidelity through behavioral alignment and structural preservation, measured by average Jensen–Shannon distance over 12 behavior attributes and 5 dialogue structure attributes, respectively. Across four corpora spanning two source families and two construction regimes, GroupPersona reduces behavioral Jensen–Shannon distance from 0.234 to 0.177 over the best-average baseline, a 24.4% reduction. It is best or tied-best on all four corpora. It maintains comparable structural distance at 0.167 versus 0.169. Together, these results show that GroupPersona improves population-level behavioral fidelity while preserving dialogue structure.
%U https://aclanthology.org/2026.findings-emnlp.663/
%P 13903-13927
Markdown (Informal)
[Beyond Individual Personas: Aligning Synthetic Dialogue to Population-Level Behavior Distributions](https://aclanthology.org/2026.findings-emnlp.663/) (Liu et al., Findings 2026)
ACL