There is a proliferation of work arguing for the use of synthetic data in scientific research. For example, social scientists are arguing for the use of LLM-generated "silicon samples" in pilot studies; AI evaluations increasingly rely on "LLM-as-a-judge" outputs; and proteomics research is accelerated by generative models that produce synthetic protein structures. These developments raise an intriguing possibility: synthetic data may help researchers ask more questions, run more studies, and accelerate discovery. But they also raise a fundamental concern: synthetic data can be biased, noisy, and misspecified. In this work, we propose statistical principles for using synthetic data in scientific research with provable validity guarantees. The key insight is a new technical condition that we call task exchangeability. Informally, this is a requirement that the researcher can identify historical tasks, for which real data is available, such that their current task of interest is exchangeable with the historical tasks in an appropriate mathematical sense. We develop methods for valid inference under task exchangeability, together with extensions that provide guarantees even beyond exchangeability. We demonstrate the framework on public opinion surveys with silicon samples and AI evaluation with autoraters.
Researchers in industry and academia use synthetic survey respondents powered by large language models as substitutes for human samples. These synthetic populations require validation against real-world data, so researchers often address them using ad hoc comparisons with human surveys. Inspired by the intention-behaviour gap in behavioural science, we argue that these validations test the wrong thing for most applied cases where decision makers commission synthetic research to anticipate consequential behaviour. To address this problem, we propose a validation framework with two requirements. First, every validity claim must state its level of correspondence with human data: does the sample predict what the represented people do, which of four diagnostics (location, dispersion, response process and structure) does the validation address, and does the validation compare against experimental effects? Second, researchers must report validity claims for subgroups, since these groups are often the most affected by consequential decisions and aggregate accuracy hides their misrepresentation. Our validation framework operationalises three justice dimensions (distributional, procedural, and recognition) as measurable quantities and defines within-persona counterfactual experiments as a validation requirement. We then apply the framework to electric vehicle charging tariffs, before closing with a reporting checklist that researchers can use to make convincing validity claims.
Florian Kutzner, Celina Kacperski, Laura de Molière +4
Synthetic tabular data are often evaluated by distributional similarity, privacy distance, or train-on-synthetic-test-on-real predictive performance, but these criteria do not ensure validity for causal inference. We show that fully generative tabular synthesizers, including GAN- and LLM-based models, can preserve predictive utility while distorting average treatment effect (ATE) estimates. The failure is structural: ATE preservation requires both a realistic covariate law and an accurate treatment-effect contrast, whereas prediction loss penalizes treatment-effect error only through an overlap-weighted term. Thus, under imbalance or limited overlap, a generator may reproduce dominant observed outcomes while underlearning intervention-relevant contrasts. We formalize this mismatch through sensitivity and loss-decomposition results. Motivated by this causal analysis and intuition, we propose a hybrid synthetic-data framework for causal inference that generates covariates while modeling treatment and outcome mechanisms separately. We evaluate the framework in three settings: ATE preservation under fully generative versus hybrid synthesis, augmentation for practical positivity problems, and diagnostic simulation engines for comparing OR, IPW, AIPW, and TMLE before real-data analysis. We also stress-test the hybrid construction across settings that vary overlap, covariate dimension, seed sample size, and treatment-effect complexity, including a logistic outcome-model misspecification check. Across controlled simulation experiments, hybrid synthesis improves causal fidelity relative to fully generative baselines; the ACTG application shows improved predictive fidelity and potential for finite-sample estimator benchmarking. LLM-based hybrid synthesis is often more faithful than CTGAN in settings where causal fidelity can be assessed.
Recent advancements in generative AI facilitate large-scale synthetic data generation for model evaluation. However, without targeted approaches, these datasets often lack the sociotechnical nuance required for sensitive domains. We introduce NodeSynth, an evidence-grounded methodology that generates socially relevant synthetic queries by leveraging a fine-tuned taxonomy generator (TaG) anchored in real-world evidence. Evaluated against four mainstream LLMs (e.g., Claude 4.5 Haiku), NodeSynth elicited failure rates up to five times higher than human-authored benchmarks. Ablation studies confirm that our granular taxonomic expansion significantly drives these failure rates, while independent validation reveals critical deficiencies in prominent guard models (e.g., Llama-Guard-3). We open-source our end-to-end research prototype and datasets to enable scalable, high-stakes model evaluation and targeted safety interventions (https://github.com/google-research/nodesynth).