no code implementations • 24 Dec 2023 • George Gui, Olivier Toubia
The second explicitly specifies the source of treatment variation in the prompt given to the LLM (e. g., by informing the LLM that the store is running an experiment).
no code implementations • 30 Dec 2021 • George Gui, Harikesh Nair, Fengshi Niu
Causally identifying the effect of digital advertising is challenging, because experimentation is expensive, and observational data lacks random variation.