@inproceedings{du-etal-2026-twinvoice,
title = "{T}win{V}oice: A Multi-dimensional Benchmark Towards Digital Twins via {LLM} Persona Simulation",
author = "Du, Bangde and
Guo, Minghao and
He, Songming and
Ye, Ziyi and
Zhu, Xi and
Su, Weihang and
Zhu, Shuqi and
Zhou, Yujia and
Zhang, Yongfeng and
Ai, Qingyao and
Liu, Yiqun",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.981/",
pages = "19604--19628",
ISBN = "979-8-89176-395-1",
abstract = "Large Language Models (LLMs) are exhibiting emergent human-like abilities and are envisioned as the tool for simulating an individual{'}s communication patterns, behaviors, and personality traits. However, current evaluations of LLM-based persona simulation remain limited: most rely on synthetic dialogues and lack fine-grained analysis of the capability for persona simulation. To address these limitations, we introduce TwinVoice, a comprehensive benchmark for assessing persona simulation across diverse real-world contexts. TwinVoice encompasses three dimensions: Social Persona (public social interactions), Interpersonal Persona (private dialogues), and Narrative Persona (role-based expression). It further decomposes the evaluation into six fundamental capabilities, including opinion consistency, memory recall, logical reasoning, lexical fidelity, persona tone, and syntactic style. Experimental results reveal that while advanced models achieve moderate accuracy in persona simulation, they still fall short of capabilities such as syntactic style and memory recall. Our data, code, and evaluation results are available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="du-etal-2026-twinvoice">
<titleInfo>
<title>TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bangde</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghao</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songming</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyi</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weihang</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuqi</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujia</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongfeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingyao</namePart>
<namePart type="family">Ai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiqun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) are exhibiting emergent human-like abilities and are envisioned as the tool for simulating an individual’s communication patterns, behaviors, and personality traits. However, current evaluations of LLM-based persona simulation remain limited: most rely on synthetic dialogues and lack fine-grained analysis of the capability for persona simulation. To address these limitations, we introduce TwinVoice, a comprehensive benchmark for assessing persona simulation across diverse real-world contexts. TwinVoice encompasses three dimensions: Social Persona (public social interactions), Interpersonal Persona (private dialogues), and Narrative Persona (role-based expression). It further decomposes the evaluation into six fundamental capabilities, including opinion consistency, memory recall, logical reasoning, lexical fidelity, persona tone, and syntactic style. Experimental results reveal that while advanced models achieve moderate accuracy in persona simulation, they still fall short of capabilities such as syntactic style and memory recall. Our data, code, and evaluation results are available.</abstract>
<identifier type="citekey">du-etal-2026-twinvoice</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.981/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>19604</start>
<end>19628</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation
%A Du, Bangde
%A Guo, Minghao
%A He, Songming
%A Ye, Ziyi
%A Zhu, Xi
%A Su, Weihang
%A Zhu, Shuqi
%A Zhou, Yujia
%A Zhang, Yongfeng
%A Ai, Qingyao
%A Liu, Yiqun
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F du-etal-2026-twinvoice
%X Large Language Models (LLMs) are exhibiting emergent human-like abilities and are envisioned as the tool for simulating an individual’s communication patterns, behaviors, and personality traits. However, current evaluations of LLM-based persona simulation remain limited: most rely on synthetic dialogues and lack fine-grained analysis of the capability for persona simulation. To address these limitations, we introduce TwinVoice, a comprehensive benchmark for assessing persona simulation across diverse real-world contexts. TwinVoice encompasses three dimensions: Social Persona (public social interactions), Interpersonal Persona (private dialogues), and Narrative Persona (role-based expression). It further decomposes the evaluation into six fundamental capabilities, including opinion consistency, memory recall, logical reasoning, lexical fidelity, persona tone, and syntactic style. Experimental results reveal that while advanced models achieve moderate accuracy in persona simulation, they still fall short of capabilities such as syntactic style and memory recall. Our data, code, and evaluation results are available.
%U https://aclanthology.org/2026.findings-acl.981/
%P 19604-19628
Markdown (Informal)
[TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation](https://aclanthology.org/2026.findings-acl.981/) (Du et al., Findings 2026)
ACL
- Bangde Du, Minghao Guo, Songming He, Ziyi Ye, Xi Zhu, Weihang Su, Shuqi Zhu, Yujia Zhou, Yongfeng Zhang, Qingyao Ai, and Yiqun Liu. 2026. TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation. In Findings of the Association for Computational Linguistics: ACL 2026, pages 19604–19628, San Diego, California, United States. Association for Computational Linguistics.