# Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents

arXiv: https://arxiv.org/abs/2608.14606 · HTML: https://mlsanity.com/paper/2608.14606/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 26 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 6 of 6)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)

## Built on by (most cited first, 8 of 8)

- [Distributional Validity of a Korean Synthetic Persona Panel: Evidence From the Korea Media Panel Survey](https://mlsanity.com/paper/2608.28615/) (2026)
- [Artificial Societies Benchmark: A Validation Framework for Synthetic Research](https://mlsanity.com/paper/2609.30030/) (2026)
- [Shared Autoregressive Context Can Distort Relationships in Synthetic Data](https://mlsanity.com/paper/2609.32546/) (2026)
- [Simulating Respondents, Not Single Questions: Coherent Survey Generation with Large Language Models](https://mlsanity.com/paper/2609.34828/) (2026)
- [RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations](https://mlsanity.com/paper/2610.01780/) (2026)
- [Behavioral History Outperforms Descriptions of the Person for LLM Synthetic Personas](https://mlsanity.com/paper/2610.03998/) (2026)
- [Probable but Not Valid: A Psychometric Audit of Decision Models as Synthetic Survey Respondents](https://mlsanity.com/paper/2610.14912/) (2026)
- [From Caricature to Collective Artifact: How Persona Construction Drives Polarization in Generative Social Simulations](https://mlsanity.com/paper/2610.16498/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used as synthetic survey respondents, but existing evaluations mostly ask whether individual answers look plausible. We ask a stricter, psychometric question: do LLMs preserve the joint distribution, latent structure, reliability, mediation pathways, and demographic effects of real human survey data? We introduce an open Lithuanian organisational-psychology dataset (n=263 employees; three validated instruments; 68 items, 12 subscales) and condition 37 LLMs on real respondent profiles under a persona-disclosure ladder, presentation, reasoning-effort and cross-language ablations, counterfactual demographic swaps, and a memorization probe. The resulting Psychometric Similarity Score (PSS) is anchored against five statistical baselines, a held-out human ceiling, and the real answers of the same respondents. LLMs reproduce the direction of human psychometric relationships, but statistical baselines with no language model match or beat them. The best LLM (PSS 0.81) is level with a Gaussian copula fit only on other respondents (0.82) and below the real answers of the same 100 people (0.89). A simple classifier separates every LLM sample from humans (median AUC 0.99), and verbatim recall of the items is rare (at most 4.7%) and unrelated to PSS. Counterfactual swaps move answers in the direction of human group differences and by a similar amount (role 0.49 and education 0.33 human SD, vs. 0.46 and 0.44 in humans). Gender swaps move them by 0.06 SD. Tucker's phi on UWES falls inside an item-permutation null for 10 of 37 models. Synthetic respondents compress the response scale (within-respondent SD 0.79 vs. 1.19), lose predictive validity on held-out humans (mean R^2=-0.14 vs. 0.28), and produce significant indirect effects on 4 of 7 mediation paths that are null in humans. LLM samples are therefore not a drop-in replacement for human survey data.