# SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulation

arXiv: https://arxiv.org/abs/2604.07513 · HTML: https://mlsanity.com/paper/2604.07513/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 58 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Matrix Completion and Low-Rank SVD via Fast Alternating Least Squares](https://mlsanity.com/paper/1410.2596/) (2014)
- [LLM Generated Persona is a Promise with a Catch](https://mlsanity.com/paper/2503.16527/) (2025)
- [Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions](https://mlsanity.com/paper/2502.16761/) (2025)
- [Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations](https://mlsanity.com/paper/2502.07068/) (2025)
- [Causal Matrix Completion](https://mlsanity.com/paper/2109.15154/) (2021)
- [Finetuning LLMs for Human Behavior Prediction in Social Science Experiments](https://mlsanity.com/paper/2509.05830/) (2025)
- [Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions](https://mlsanity.com/paper/2502.20897/) (2025)
- [This human study did not involve human subjects: Validating LLM simulations as behavioral evidence](https://mlsanity.com/paper/2602.15785/) (2026)
- [The Augmented Synthetic Control Method](https://mlsanity.com/paper/1811.04170/) (2018)
- [Mixture-of-Personas Language Models for Population Simulation](https://mlsanity.com/paper/2504.05019/) (2025)
- [How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspective](https://mlsanity.com/paper/2502.17773/) (2025)
- [Digital Twins as Funhouse Mirrors: Five Key Distortions](https://mlsanity.com/paper/2509.19088/) (2025)
- [Human Digital Twin: A Survey](https://mlsanity.com/paper/2212.05937/) (2022)
- [Cybonto: Towards Human Cognitive Digital Twins for Cybersecurity](https://mlsanity.com/paper/2108.00551/) (2021)

## Built on by (most cited first, 2 of 2)

- [Adaptive Querying with AI Persona Priors](https://mlsanity.com/paper/2605.00696/) (2026)
- [LLM-Powered Virtual Population for Demand Simulation and Pricing](https://mlsanity.com/paper/2606.16183/) (2026)

## Abstract (arXiv)

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.