6 citations · 7 across the 4 of their papers we have counts for
5 papers
ExploraTwin, a Non-Profit Research Platform for Digital Twin Simulations
Naveen Venkat, Yuchen Qiu, Tianyi Peng +2
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 fric…
Leveraging LLMs to Improve Experimental Design: A Generative Stratification Approach
George Gui, Seungwoo Kim
Pre-experiment stratification, or blocking, is a well-established technique for designing more efficient experiments and increasing the precision of the experimental estimates. How…
Digital Twins as Funhouse Mirrors: Five Key Distortions
Tianyi Peng, George Gui, Melanie Brucks +20
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-reg…
Modeling Story Expectations: A Generative Framework using LLMs
Hortense Fong, George Gui, Bo Yang
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 r…
Combining Observational and Experimental Data to Improve Efficiency Using Imperfect Instruments
George Z. Gui
Randomized controlled trials generate experimental variation that can credibly identify causal effects, but often suffer from limited scale, while observational datasets are large,…