arXiv Computation and Language

SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulation

SYN-DIGITS is a model‑agnostic, post‑hoc calibration framework that uses relationships learned from digital twin simulations to predict human responses, especially in cold‑start scenarios where no target question data is available. It transfers these relationships to improve individual‑level correlation and distributional predictions, even when only marginal reference data is available. Experiments on three datasets and thirteen persona constructions show significant gains—up to 417% improvement in correlation and 57% reduction in distributional error—over uncalibrated baselines.

arXiv AI

Sep 15

Synthetic Data in Marketing Research: How to Evaluate and When to Trust

The paper discusses the use of synthetic data in marketing research, arguing that the key question is not whether synthetic respondents work, but when they do. It categorizes synthetic data into three types—ungrounded LLM responses, segment-level personas, and individual-level digital twins—and maps each to the decisions they can support. The authors also propose a taxonomy of accuracy measures, highlight the forgotten question problem, and introduce an ex‑ante answerability diagnostic based on R² to improve twin-human correlation.

By Oded Netzer, Rajan Sambandam

llms rag

arXiv AI

Sep 10

When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutability

arXiv:2609.07987v1 Announce Type: new Abstract: LLM-based digital twins promise to reduce repeated human data collection by generating person- specific responses, yet existing evaluations provide lit...

By Steven Wang, Kyle Hunt, Shaojie Tang, Kenneth Joseph

llms

arXiv Computation and Language

Aug 24

Beyond Raw Transcripts: Structured Persona Extraction for LLM-Based Digital Twins

arXiv:2608.20344v1 Announce Type: new Abstract: LLM-based "digital twins" aim to simulate how an individual would behavein new environments or respond to novel questions, given some representation of...

By Iris Ye, Tianze Deng, Ozan Candogan

llms benchmarks

arXiv AI

Oct 7

Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes

arXiv:2610.05828v2 Announce Type: replace Abstract: Large language models (LLMs) offer new opportunities for public opinion research by enabling early prediction of survey responses, potentially redu...

By Dongryeol Lee, Weronika {\L}ajewska, Leonardo Perelli, Saab Mansour

llms agents fine-tuning safety

arXiv AI

Sep 25

AI-Moderated Interviews for Market Research and Digital Twins Calibration

AI‑moderated interviews are a scalable market‑research method that can match human moderation in depth, cover more themes, and recover more customer needs while keeping budgets constant. Participants, however, feel more emotionally engaged with live humans. Digital twins built from AI‑moderated data predict consumer responses better than demographics‑only personas, but the added richness does not improve quantitative predictions over static interviews, and prediction errors stem from differences in thinking styles and data‑distribution gaps.

By Yuting Deng, Jingxuan Liu, Olivier Toubia, Naman Jain

arXiv AI

Jun 4

Synthetic Personalities: How Well Can LLMs Mimic Individual Respondents Using Socio-Economic Microdata?

arXiv:2606. 04592v1 Announce Type: cross Abstract: LLM-based digital twins promise to scale and accelerate market research, but most published twins are either coarse persona bots conditioned on a few demographic questions or detailed individual-level twins built on purpose-collected surveys and interview transcripts.

By Leonard Kinzinger, Jochen Hartmann

llms rag

arXiv AI

Jul 31

When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses

arXiv:2607. 26348v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as synthetic users, stand-ins for human respondents whose simulated answers feed product, policy, and market decisions.

By Zihan Chen, Di Zhu, Lei Nico Zheng

llms benchmarks

arXiv Computation and Language

Oct 15

When Can Digital Personas Reliably Approximate Human Survey Findings?

arXiv:2605.10659v3 Announce Type: replace Abstract: Digital personas powered by Large Language Models (LLMs) are increasingly proposed as substitutes for human survey respondents, yet it remains uncl...

By Mumin Jia, Yilin Chen, Divya Sharma, Jairo Diaz-Rodriguez

llms rag safety

arXiv AI

Jun 18

How Well Do Large Language Models Capture Human Personality?

arXiv:2606. 18263v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to simulate human populations via persona prompting, often under the assumptions that richer persona descriptions improve behavioral fidelity, similarly sized attribute combinations are equally simulatable, and persona definitions generalize across tasks.

By Aanisha Bhattacharyya, Yaman Kumar Singla, Rajiv Ratn Shah, Changyou Chen, Jitendra Ajmera

llms diffusion safety

arXiv Computation and Language

Sep 22

Pretrained Persona Mixture Models and Tandem Models for Human Simulation

arXiv:2609.22607v1 Announce Type: new Abstract: We argue here that the current dominant practice in LLM human simulation: prompting instruction-tuned assistant language models to role-play personas,...

By Minwoo Kang, T\'ea Wright, Seun Eisape, Ayush Raj, Suhong Moon, Joseph Suh, Alane Suhr, David M. Chan, John Canny

llms

arXiv AI

Aug 5

Emulate or Estimate? The Divergent Strengths of Base and Post-Trained Language Models for Opinion Simulation

arXiv:2608. 03044v1 Announce Type: cross Abstract: Large language models are increasingly used to simulate human opinions, but prior work reports conflicting results: some studies find promising alignment with human survey data, while others find persona collapse and weak demographic sensitivity.

By Seth Grief-Albert, Jessica Bo, Difan Jiao, Ashton Anderson

llms safety

arXiv AI

Jul 14

AI YOU Town: Make Friends and Money with Your Digital Twin

arXiv:2607. 10539v1 Announce Type: new Abstract: Existing approaches to infer user traits and generate responses consistent with a persona rely on static prompting.

By Yan Lin, Yuyang Dai, Jiahui Geng, Yuxia Wang

llms agents safety

Related stories