arXiv subjects

George Gui

Publications and source records attributed to George Gui.

8 recordsLinked to original sources

arXiv2026

ExploraTwin, a Non-Profit Research Platform for Digital Twin Simulations

Digital twin simulations show promise, but current empirical evidence suggests that the approach should be tested before being deployed in any particular context. To lower the friction for researchers and practitioners to test and deploy digital twin simulations, this brief commentary introduces ExploraTwin (https://exploratwin.org), an open-access, non-profit research platform for digital twin survey simulations. ExploraTwin supports two modes. In survey mode, researchers can upload a Qualtrics survey file or create a survey within the platform; select an available sample of digital twins; configure and run the simulation, and export analysis-ready data. In panel mode, researchers can assemble a small group of twins for open-ended conversations, document annotation, and moderated, focus-group-style voice discussions. We also developed CroissantTwin, a standardized data format for adding samples of digital twins to the platform. We demonstrate the survey mode workflow by using the platform to replicate 19 experiments on digital twins from the Twin-2K-500 dataset. ExploraTwin's survey execution fidelity is high: 99.6% of 197,000 answer units returned a structurally valid response on the first run.

cs.CY↗

arXiv2025

Leveraging LLMs to Improve Experimental Design: A Generative Stratification Approach

Pre-experiment stratification, or blocking, is a well-established technique for designing more efficient experiments and increasing the precision of the experimental estimates. However, when researchers have access to many covariates at the experiment design stage, they often face challenges in effectively selecting or weighting covariates when creating their strata. This paper proposes a Generative Stratification procedure that leverages Large Language Models (LLMs) to synthesize high-dimensional covariate data to improve experimental design. We demonstrate the value of this approach by applying it to a set of experiments and find that our method would have reduced the variance of the treatment effect estimate by 10%-50% compared to simple randomization in our empirical applications. When combined with other standard stratification methods, it can be used to further improve the efficiency. Our results demonstrate that LLM-based simulation is a practical and easy-to-implement way to improve experimental design in covariate-rich settings.

econ.EM↗

arXiv2025

Digital Twins as Funhouse Mirrors: Five Key Distortions

Scientists and practitioners are increasingly moving to deploy digital twins--LLM-based models of real individuals--across social science and policy research. We conduct 19 pre-registered studies spanning 164 diverse outcomes (e.g., attitudes toward hiring algorithms, intentions to share misinformation), comparing human responses to those of their corresponding digital twins, which are trained on each individual's prior responses to over 500 questions. We establish an empirical benchmark for digital twin performance: their predictions are only modestly more accurate than those of a homogeneous base LLM and exhibit weak correlation with human responses (average $r = 0.20$). To inform future development, we identify five systematic distortions in digital twin behavior: (i) insufficient individuation, (ii) stereotyping, (iii) representation bias, (iv) ideological bias, and (v) hyper-rationality. Finally, we release our full dataset and code as a standardized testbed for evaluating and improving digital twin methodologies. Together, our findings caution against premature deployment while laying the groundwork for a transparent, replicable, and iterative science of responsible digital twin development.

cs.CY↗

arXiv2024

Modeling Story Expectations: A Generative Framework using LLMs

Consumers' engagement with stories is shaped by their expectations about what will happen next, yet modeling these forward-looking beliefs over unstructured narrative content has remained challenging. We develop a framework that uses large language models to approximate consumers' story expectations. Our method generates multiple imagined story continuations from a pre-trained LLM and extracts interpretable, theory-motivated features from these continuations, such as emotion and narrative path features. We propose two complementary validation procedures suited to different data availability: a survey-based approach that compares LLM-derived expectations to human-reported beliefs, and a rational-expectations approach that compares them to actual story outcomes. Applying the framework to both survey data collected in a controlled lab setting and observational data from an online reading platform, we find that LLM-derived expectations correlate with human-reported beliefs as well as actual story continuations along all features studied. In both settings, forward-looking expectations are associated with reader engagement above and beyond features of the content already consumed. Our framework provides a scalable method for modeling consumer beliefs about narrative content, with implications for content creation, platform strategy, and the study of narrative media.

cs.CL↗

arXiv2023

The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspective

Large Language Models (LLMs) have shown impressive potential to simulate human behavior. We identify a fundamental challenge in using them to simulate experiments: when LLM-simulated subjects are blind to the experimental design (as is standard practice with human subjects), variations in treatment systematically affect unspecified variables that should remain constant, violating the unconfoundedness assumption. Using demand estimation as a context and an actual experiment with 40 different products as a benchmark, we show this can lead to implausible results. While confounding may in principle be addressed by controlling for covariates, this can compromise ecological validity in the context of LLM simulations: controlled covariates become artificially salient in the simulated decision process. We show formally that confoundness stems from ambiguous prompting strategies. Therefore, it can be addressed by developing unambiguous prompting strategies through unblinding, i.e., revealing the experiment design in LLM simulations. Our empirical results show that this strategy consistently enhances model performance across all tested models, including both out-of-box reasoning and non-reasoning models. We also show that it is a technique that complements fine-tuning: while fine-tuning can improve simulation performance, an unambiguous prompting strategy makes the predictions robust to the inclusion of irrelevant data in the fine-tuning process.

cs.AI↗

arXiv2022

Auction Throttling and Causal Inference of Online Advertising Effects

Causally identifying the effect of digital advertising is challenging, because experimentation is expensive, and observational data lacks random variation. This paper identifies a pervasive source of naturally occurring, quasi-experimental variation in user-level ad-exposure in digital advertising campaigns. It shows how this variation can be utilized by ad-publishers to identify the causal effect of advertising campaigns. The variation pertains to auction throttling, a probabilistic method of budget pacing that is widely used to spread an ad-campaign`s budget over its deployed duration, so that the campaign`s budget is not exceeded or overly concentrated in any one period. The throttling mechanism is implemented by computing a participation probability based on the campaign`s budget spending rate and then including the campaign in a random subset of available ad-auctions each period according to this probability. We show that access to logged-participation probabilities enables identifying the local average treatment effect (LATE) in the ad-campaign. We present a new estimator that leverages this identification strategy and outline a bootstrap procedure for quantifying its variability. We apply our method to real-world ad-campaign data from an e-commerce advertising platform, which uses such throttling for budget pacing. We show our estimate is statistically different from estimates derived using other standard observational methods such as OLS and two-stage least squares estimators. Our estimated conversion lift is 110%, a more plausible number than 600%, the conversion lifts estimated using naive observational methods.

econ.EM↗

arXiv2018

A Memo on the Proof-of-Stake Mechanism

We analyze the economic incentives generated by the proof-of-stake mechanism discussed in the Ethereum Casper upgrade proposal. Compared with proof-of-work, proof-of-stake has a different cost structure for attackers. In Budish (2018), three equations characterize the limits of Bitcoin, which has a proof-of-work mechanism. We investigate their counterparts and evaluate the risk of double-spending attack and sabotage attack. We argue that PoS is safer than PoW agaisnt double-spending attack because of the tractability of attackers, which implies a large "stock" cost for the attacker. Compared to a PoW system whose mining equipments are repurposable, PoS is also safer against a sabotage attack.

cs.CR↗

arXiv2018

Finding Exogenous Variation in Data

We reconsider the classic problem of recovering exogenous variation from an endogenous regressor. Two-stage least squares recovers exogenous variation through presuming the existence of an instrumental variable. We rely instead on the assumption that the regressor is a mixture of exogenous and endogenous observations--say as the result of temporary natural experiments. With this assumption, we propose an alternative two-stage method based on nonparametrically estimating a mixture model to recover a subset of the exogenous observations. We demonstrate that our method recovers exogenous observations in simulation and can be used to find pricing experiments hidden in grocery store scanner data.

stat.AP↗