NBER Paper: Using LLMs to Generate and Validate Economic Theories

soumitrashukla9 · x · 2026-07-30

Researchers are highlighting key literature on applying Large Language Models (LLMs) to academic theory building. Recommendations include Annie Liang's forthcoming JEL paper, Using Machine Learning to Generate, Clarify, and Improve Economic Models.

Additionally, an NBER working paper introduces GABE (Generative AI-Based Experimentation), a framework using LLMs to simulate complex real-world organizational settings with multiple agents. The study shows this approach can replicate human subject experiments at a fraction of the cost, while unpacking decision-making mechanisms to accelerate strategic theory building in the social sciences.

Original post →

More from Research

Research channel →