Augmenting Survey Data with Generative AI: An Application to Economic Research

We study the potential of large language models (LLMs) to augment survey data collected from human subjects, by focusing on two applications: (1) estimating willingness-to-accept (WTA) for giving up digital and traditional goods, and (2) predicting personal income levels.

We find that supplying LLMs with rich contextual data beyond demographics significantly improves predictive accuracy. Model fine tuning and retrieval augmented generation (RAG) further enhance performance, while changes to model temperature or prompting strategies yield only marginal improvements. Performance varies across goods studied and demographic groups. We provide a methodological blueprint for deploying LLMs as a fast, low cost multiplier of survey coverage. This is increasingly valuable given the rapid decline in survey response rates.