# LLM-Mirror: A Generated-Persona Approach for Survey Pre-Testing

arXiv: https://arxiv.org/abs/2412.03162 · HTML: https://mlsanity.com/paper/2412.03162/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2024.

## Built on by (most cited first, 7 of 7)

- [Overstating Attitudes, Ignoring Networks: LLM Biases in Simulating Misinformation Susceptibility](https://mlsanity.com/paper/2602.04674/) (2026)
- [Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication](https://mlsanity.com/paper/2505.21451/) (2025)
- [Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data](https://mlsanity.com/paper/2606.28963/) (2026)
- [Sentiment Simulation using Generative AI Agents](https://mlsanity.com/paper/2505.22125/) (2025)
- [Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation](https://mlsanity.com/paper/2510.13884/) (2025)
- [The Pragmatic Persona: Discovering LLM Persona through Bridging Inference](https://mlsanity.com/paper/2604.24079/) (2026)
- [Item-Mean Surrogates: Why Richer Persona Data Fail to Improve LLMs as Human Surrogates](https://mlsanity.com/paper/2608.29455/) (2026)

## Abstract (arXiv)

Surveys are widely used in social sciences to understand human behavior, but their implementation often involves iterative adjustments that demand significant effort and resources. To this end, researchers have increasingly turned to large language models (LLMs) to simulate human behavior. While existing studies have focused on distributional similarities, individual-level comparisons remain underexplored. Building upon prior work, we investigate whether providing LLMs with respondents' prior information can replicate both statistical distributions and individual decision-making patterns using Partial Least Squares Structural Equation Modeling (PLS-SEM), a well-established causal analysis method. We also introduce the concept of the LLM-Mirror, user personas generated by supplying respondent-specific information to the LLM. By comparing responses generated by the LLM-Mirror with actual individual survey responses, we assess its effectiveness in replicating individual-level outcomes. Our findings show that: (1) PLS-SEM analysis shows LLM-generated responses align with human responses, (2) LLMs, when provided with respondent-specific information, are capable of reproducing individual human responses, and (3) LLM-Mirror responses closely follow human responses at the individual level. These findings highlight the potential of LLMs as a complementary tool for pre-testing surveys and optimizing research design.