mlsanityData to 7 Oct 2026

LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models

arXiv 2505.14752 ↗First posted 20 May 2025cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 55 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

28 of 55 references.

References · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  6. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  7. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
  8. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
  9. 2022Language Models are Realistic Tabular Data Generatorscited by 290
  10. 2023Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Biascited by 230
  11. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 183
  12. 2024Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generationcited by 99
16 more
  1. 2022STaSy: Score-based Tabular data Synthesiscited by 85
  2. 2024Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Modelscited by 71
  3. 2020VAEM: a Deep Generative Model for Heterogeneous Mixed Type Datacited by 66
  4. 2023Language Models as Zero-Shot Trajectory Generatorscited by 59
  5. 2024Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuningcited by 57
  6. 2019Conscientious Classification: A Data Scientist's Guide to Discrimination-Aware Classificationcited by 55
  7. 2022Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Citiescited by 38
  8. 2021Copula Flows for Synthetic Data Generationcited by 35
  9. 2024ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planningcited by 33
  10. 2024Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challengescited by 30
  11. 2024HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protectioncited by 16
  12. 2025Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMscited by 15
  13. 2024An improved tabular data generator with VAE-GMM integrationcited by 13
  14. 2022Effective Seed-Guided Topic Discovery by Integrating Multiple Types of Contextscited by 12
  15. 2023Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answeringcited by 5
  16. 2024Mastering the Craft of Data Synthesis for CodeLLMscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Using Zero-Shot LLM-Generated Survey Data for Geographically Explicit Population Synthesiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data
  2. 2026Do LLMs Know Your Neighborhood? Auditing LLM Priors for Neighborhood-Level Mobility Prediction and Structural Alignment
  3. 2025FASTGEN: Fast and Cost-Effective Synthetic Tabular Data Generation with LLMs
  4. 2025Distribution Shift Alignment Helps LLMs Simulate Survey Response Distributions
  5. 2025Evaluating the Use of Large Language Models as Synthetic Social Agents in Social Science Research
  6. 2025LLM-based Agent Simulation for Maternal Health Interventions: Uncertainty Estimation and Decision-focused Evaluation
  7. 2026A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges
  8. 2025Valid Inference with Imperfect Synthetic Data