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.
More from Research
- Many 2026 AI Papers Still Cite GPT-4 in Their Methods — emollick · 2026-07-30
- Meituan Open-Sources CAST: Using Game Solvers as Turn-Level Teachers for LLMs — meituan-longcat · 2026-07-30
- Qwen Team Introduces DecoEvo: Co-Evolving Solvers and Rubrics in Text Space — QwenBusinessUnit · 2026-07-30
- OfficeVal Benchmark: LLMs Cheaper Than Humans on Office Tasks, But Lag in Quality — Jingbo Zhou · 2026-07-30
- StealthBench: Measuring Operational Stealth in Autonomous Security Agents — Ads Dawson · 2026-07-30
- Classic MIT Lecture: Patrick Winston Breaks Down the Simplest Neural Network — tetsuoai · 2026-07-30