LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models
This addresses a data scarcity problem for researchers in social science, economics, and urban studies who need credible simulations but only have macro-level data.
The researchers tackled the problem of generating realistic individual-level data (micro-records) that align with aggregate statistics (macro-statistics) for social science simulations, where collecting such fine-grained data is impractical. They developed LLMSynthor, which uses a pretrained large language model as a simulator to iteratively generate synthetic datasets that minimize discrepancies with target aggregates, achieving strong realism and statistical fidelity across domains like mobility and e-commerce.
Macro-aligned micro-records are crucial for credible simulations in social science and urban studies. For example, epidemic models are only reliable when individual-level mobility and contacts mirror real behavior, while aggregates match real-world statistics like case counts or travel flows. However, collecting such fine-grained data at scale is impractical, leaving researchers with only macro-level data. LLMSynthor addresses this by turning a pretrained LLM into a macro-aware simulator that generates realistic micro-records consistent with target macro-statistics. It iteratively builds synthetic datasets: in each step, the LLM generates batches of records to minimize discrepancies between synthetic and target aggregates. Treating the LLM as a nonparametric copula allows the model to capture realistic joint dependencies among variables. To improve efficiency, LLM Proposal Sampling guides the LLM to propose targeted record batches, specifying variable ranges and counts, to efficiently correct discrepancies while preserving realism grounded in the model's priors. Evaluations across domains (mobility, e-commerce, population) show that LLMSynthor achieves strong realism, statistical fidelity, and practical utility, making it broadly applicable to economics, social science, and urban studies.