SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulation
This addresses reliability issues in digital twin simulations for applications like market research and recommender systems, though it is an incremental improvement as a post-processing layer on existing methods.
The paper tackles the problem of systematic bias and miscalibration in AI-based digital twin simulations using large language models, proposing SYN-DIGITS, a calibration framework that achieves up to 50% relative improvements in individual-level correlation and 50–90% relative reductions in distributional discrepancy compared to uncalibrated baselines.
AI-based persona simulation -- often referred to as digital twin simulation -- is increasingly used for market research, recommender systems, and social sciences. Despite their flexibility, large language models (LLMs) often exhibit systematic bias and miscalibration relative to real human behavior, limiting their reliability. Inspired by synthetic control methods from causal inference, we propose SYN-DIGITS (SYNthetic Control Framework for Calibrated DIGItal Twin Simulation), a principled and lightweight calibration framework that learns latent structure from digital-twin responses and transfers it to align predictions with human ground truth. SYN-DIGITS operates as a post-processing layer on top of any LLM-based simulator and thus is model-agnostic. We develop a latent factor model that formalizes when and why calibration succeeds through latent space alignment conditions, and we systematically evaluate ten calibration methods across thirteen persona constructions, three LLMs, and two datasets. SYN-DIGITS supports both individual-level and distributional simulation for previously unseen questions and unobserved populations, with provable error guarantees. Experiments show that SYN-DIGITS achieves up to 50% relative improvements in individual-level correlation and 50--90% relative reductions in distributional discrepancy compared to uncalibrated baselines.