When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutability

• URL: http://arxiv.org/abs/2609.07987v1
• Date: Mon, 07 Sep 2026 21:05:51 GMT
• Title: When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutability
• Abstract summary: Digital twins promise to reduce repeated human data collection by generating person- specific responses.<n>We introduce statistical substitutability, an inferential criterion that evaluates extent to which twin predictions can reduce human measurement.<n>We find that digital twins can reproduce average human effects while providing little information about which individuals differ from those averages.
• Score: 9.310571879281186
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-based digital twins promise to reduce repeated human data collection by generating person- specific responses, yet existing evaluations provide little evidence about whether they can reduce human measurement while preserving valid inference. To address this, we introduce statistical substitutability, an inferential criterion that evaluates the extent to which twin predictions can reduce human measurement for a particular estimand while preserving valid inference. We develop a framework, grounded in mixed-subject and prediction-powered inference, that evaluates statistical substitutability along four dimensions: aggregate fidelity, paired respondent-level signal, finite-sample human-label recovery, and stability across populations. Across two empirical evaluations spanning behavioral experiments, multiple models, and alternative respondent representations, we find that digital twins can reproduce average human effects while providing little information about which individuals differ from those averages. Newer models and richer respondent information improve some dimensions of performance but do not reliably translate into human-data savings. Human calibration can reduce aggregate prediction error, yet limited labeled samples often fail to produce stable precision gains. Importantly, these findings demonstrate that behavioral fidelity is neither necessary nor sufficient for statistical substitutability. More broadly, they suggest that AI-generated evidence should be evaluated based on its ability to support valid scientific inference rather than its ability to reproduce human outcomes alone. Digital twins should therefore be judged for confirmatory use by whether they reduce uncertainty about human quantities, not merely by whether they reproduce human means, distributions, or effects.

Related papers

• This human study did not involve human subjects: Validating LLM simulations as behavioral evidence [15.56427716190418]
  Heuristic approaches seek to establish that simulated and observed human behavior are interchangeable.<n> statistical calibration combines auxiliary human data with statistical adjustments to account for discrepancies between observed and simulated responses.
  arXiv  Detail & Related papers  (2026-02-17T18:18:38Z)
• Can Finetuing LLMs on Small Human Samples Increase Heterogeneity, Alignment, and Belief-Action Coherence? [9.310571879281186]
  Large language models (LLMs) can serve as substitutes for human participants in survey and experimental research.<n>LLMs often fail to align with real human behavior, exhibiting limited diversity, systematic misalignment for minority subgroups, insufficient within-group variance, and discrepancies between stated beliefs and actions.<n>This study examines whether fine-tuning on a small subset of human survey data, such as that obtainable from a pilot study, can mitigate these issues and yield realistic simulated outcomes.
  arXiv  Detail & Related papers  (2025-11-26T09:50:42Z)
• A Mega-Study of Digital Twins Reveals Strengths, Weaknesses and Opportunities for Further Improvement [3.418816254588274]
  Digital representations of individuals ("digital twins") promise to transform social science and decision-making.<n>We conducted 19 studies with a representative U.S. panel and their digital twins.<n>Twins reproduced individual responses with 75% accuracy and seemingly low correlation with human answers.
  arXiv  Detail & Related papers  (2025-09-23T14:42:14Z)
• Prediction-Powered Causal Inferences [59.98498488132307]
  We focus on Prediction-Powered Causal Inferences (PPCI)<n>We first show that conditional calibration guarantees valid PPCI at population level.<n>We then introduce a sufficient representation constraint transferring validity across experiments.
  arXiv  Detail & Related papers  (2025-02-10T10:52:17Z)
• Targeted Data Fusion for Causal Survival Analysis Under Distribution Shift [46.84912148188679]
  Causal inference across multiple data sources offers a promising avenue to enhance the generalizability and replicability of scientific findings.<n>Existing approaches fail to address the unique challenges of survival analysis, such as censoring and the integration of discrete and continuous time.<n>We propose two novel methods for estimating target site-specific causal effects in multi-source settings.
  arXiv  Detail & Related papers  (2025-01-30T23:21:25Z)
• Beyond correlation: The Impact of Human Uncertainty in Measuring the Effectiveness of Automatic Evaluation and LLM-as-a-Judge [51.93909886542317]
  We show how *relying on a single aggregate correlation score* can obscure fundamental differences between human labels and those from automatic evaluation.<n>We propose stratifying data by human label uncertainty to provide a more robust analysis of automatic evaluation performance.
  arXiv  Detail & Related papers  (2024-10-03T03:08:29Z)
• Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP [84.08476873280644]
  Just 13% of papers had (i) sufficiently low barriers to reproduction, and (ii) enough obtainable information, to be considered for reproduction. As a result, we had to change our coordinated study design from a reproduce approach to a standardise-then-reproduce-twice approach.
  arXiv  Detail & Related papers  (2023-05-02T17:46:12Z)
• Toward Reliable Human Pose Forecasting with Uncertainty [51.628234388046195]
  We develop an open-source library for human pose forecasting, including multiple models, supporting several datasets. We devise two types of uncertainty in the problem to increase performance and convey better trust.
  arXiv  Detail & Related papers  (2023-04-13T17:56:08Z)
• Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes [52.92110730286403]
  It is commonly believed that the marginal likelihood should be reminiscent of cross-validation metrics and that both should deteriorate with larger input dimensions. We prove that by tuning hyper parameters, the performance, as measured by the marginal likelihood, improves monotonically with the input dimension. We also prove that cross-validation metrics exhibit qualitatively different behavior that is characteristic of double descent.
  arXiv  Detail & Related papers  (2022-10-14T08:09:33Z)
• Empirical Estimates on Hand Manipulation are Recoverable: A Step Towards Individualized and Explainable Robotic Support in Everyday Activities [80.37857025201036]
  Key challenge for robotic systems is to figure out the behavior of another agent. Processing correct inferences is especially challenging when (confounding) factors are not controlled experimentally. We propose equipping robots with the necessary tools to conduct observational studies on people.
  arXiv  Detail & Related papers  (2022-01-27T22:15:56Z)
• Targeting Underrepresented Populations in Precision Medicine: A Federated Transfer Learning Approach [7.467496975496821]
  We propose a two-way data integration strategy that integrates heterogeneous data from diverse populations and from multiple healthcare institutions. We show that the proposed method improves the estimation and prediction accuracy in underrepresented populations, and reduces the gap of model performance across populations.
  arXiv  Detail & Related papers  (2021-08-27T04:04:34Z)
• Double Robust Representation Learning for Counterfactual Prediction [68.78210173955001]
  We propose a novel scalable method to learn double-robust representations for counterfactual predictions. We make robust and efficient counterfactual predictions for both individual and average treatment effects. The algorithm shows competitive performance with the state-of-the-art on real world and synthetic data.
  arXiv  Detail & Related papers  (2020-10-15T16:39:26Z)
• Enabling Counterfactual Survival Analysis with Balanced Representations [64.17342727357618]
  Survival data are frequently encountered across diverse medical applications, i.e., drug development, risk profiling, and clinical trials. We propose a theoretically grounded unified framework for counterfactual inference applicable to survival outcomes.
  arXiv  Detail & Related papers  (2020-06-14T01:15:00Z)
• Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction [6.170898159041278]
  We present a novel variational recurrent network that estimates the distribution of missing variables, updates hidden states, and predicts the possibility of in-hospital mortality. It is noteworthy that our model can conduct these procedures in a single stream and learn all network parameters jointly in an end-to-end manner.
  arXiv  Detail & Related papers  (2020-03-02T04:41:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.