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.
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.
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.
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...
arXiv:2603. 00059v3 Announce Type: replace-cross Abstract: How well can AI-derived synthetic research data replicate the responses of human participants?
arXiv:2601. 14264v2 Announce Type: replace-cross Abstract: Large language models (LLMs) act as digital twins for human respondents, yet their psychometric comparability remains uncertain.
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...
arXiv:2607. 26060v1 Announce Type: cross Abstract: LLM-based chatbots are transforming customer service in regulated domains such as banking, but scalable and cost-effective validation remains a critical barrier to safe deployment.
ExploraTwin is an open‑access, non‑profit research platform designed to lower the friction for testing and deploying digital twin simulations. It offers two modes: a survey mode that lets researchers upload or create surveys, select digital twin samples, run simulations, and export analysis‑ready data; and a panel mode that supports small groups of twins for open‑ended conversations, annotation, and moderated voice discussions. The platform also introduced CroissantTwin, a standardized data format for adding twin samples, and demonstrated high fidelity in survey execution with 99.6% valid responses across 197,000 answer units.
arXiv:2509. 02910v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly act on people's behalf: they write emails, buy groceries, and book restaurants.
arXiv:2607. 11039v1 Announce Type: cross Abstract: Young job seekers frequently turn to social media to compare themselves with peers and make sense of career possibilities.
arXiv:2606. 16475v1 Announce Type: cross Abstract: Many societal decisions are settled by contests of persuasion.
The paper investigates whether human psychometric questionnaires can reliably characterize large language models (LLMs) in everyday interactions. By comparing eight open‑source LLMs’ value and personality profiles from Likert self‑reports (PVQ‑40/21 and BFI‑44/10) with generation probabilities on value‑laden user queries, the authors find substantial divergence between the two methods. The study shows that questionnaire items contain explicit lexical cues that lead models to respond in socially desirable ways, whereas realistic user queries lack such cues, and demographic persona prompts shift questionnaire responses but not generation outputs, indicating that questionnaire scores overestimate LLMs’ true behavioral tendencies.