Overview

Synthetic data evaluation asks whether generated examples are realistic and suitable for their intended use, such as model training, scientific inference, or benchmarking. Researchers combine distributional and dependence metrics with train-on-synthetic, test-on-real experiments, human or expert review, domain-specific checks, and privacy attacks. Controlled benchmarks with known structure can test whether methods preserve causal, temporal, subgroup, or task-relevant properties that ordinary summary statistics may miss. A central open challenge is that no single fidelity score reliably predicts utility or privacy: results depend on the task, data domain, and evaluation protocol.

Latest papers

CardsList

255 papers20 papers in the last four weeks, down 35% on the four weeks before. 0.2% of all new papers.

  1. SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data

    Feb 16, 2026David Chanin, Adrià Garriga-AlonsoSparse AutoencodersSynthetic Benchmark Generation

  2. Stochastic Parrots or Singing in Harmony? Testing Five Leading LLMs for their Ability to Replicate a Human Survey with Synthetic Data

    Feb 10, 2026Jason Miklian, Kristian Hoelscher, John E. KatsosHuman Behavior SimulationSynthetic Data Generation

  3. Synthetic Time Series Generation via Complex Networks

    Jan 30, 2026Jaime Vale, Vanessa Freitas Silva, Maria Eduarda Silva +1Time Series GenerationSynthetic Data Evaluation

  4. Interpretable Similarity of Synthetic Image Utility

    Dec 18, 2025Panagiota Gatoula, George Dimas, Dimitris K. IakovidisMedical Image SynthesisSynthetic Data Evaluation

  5. From Simulation to Experiment: Benchmarking Machine-Learning Models for Quantum-Dot State Recognition

    Nov 27, 2025Valeria Díaz Moreno, Ryan P Khalili, Daniel Schug +3Sim-to-Real TransferSynthetic Data Evaluation

  6. Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence

    Oct 18, 2025Bingji Yi, Qiyuan Liu, Yuwei Cheng +1Synthetic Data PretrainingModel Collapse

  7. SynBench: A Benchmark for Differentially Private Text Generation

    Sep 18, 2025Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar +9Differentially Private Synthetic Data GenerationPrivacy-Preserving Language Models

  8. Generating Individual Travel Diaries Using Large Language Models Informed by Census and Land-Use Data

    Sep 7, 2025Sepehr Golrokh Amin, Devin Rhoads, Fatemeh Fakhrmoosavi +2Synthetic Data GenerationSynthetic Data Evaluation

  9. MAGneT: Coordinated Multi-Agent Generation of Synthetic Multi-Turn Mental Health Counseling Sessions

    Sep 4, 2025Aishik Mandal, Tanmoy Chakraborty, Iryna GurevychMental Health CounselingMental Health

  10. Synthetic data for ratemaking: imputation-based methods vs adversarial networks and autoencoders

    Sep 2, 2025Yevhen Havrylenko, Meelis Käärik, Artur TuttarSynthetic Data AugmentationSynthetic Tabular Data Generation

  11. Can synthetic data reproduce real-world findings in epidemiology? A replication study using adversarial random forests

    Aug 19, 2025Jan Kapar, Kathrin Günther, Lori Ann Vallis +27Synthetic Tabular Data GenerationSynthetic Data Evaluation

  12. OmniFall: From Staged Through Synthetic to Wild, A Unified Multi-Domain Dataset for Robust Fall Detection

    May 26, 2025David Schneider, Zdravko Marinov, Moritz Mistol +6Synthetic-to-Real Domain AdaptationFall Detection

  13. Causality for Tabular Data Synthesis: A High-Order Structure Causal Benchmark Framework

    Jun 12, 2024Zineb Senane, Axel Karlsson, Lele Cao +6Synthetic Benchmark GenerationCausal Inference

  14. Incorporating synthetic data from diffusion models supports echocardiography downstream tasks

    Mar 28, 2024Milad Yazdani, Pooria Ashrafian, Moein Heidari +3EchocardiographyDiffusion-Based Data Augmentation

  15. AI-Generated Images as Data Source: The Dawn of Synthetic Era

    Oct 3, 2023Zuhao Yang, Yu Wei, Fangneng Zhan +5Synthetic Data AugmentationSynthetic Data Generation