Journal of Economic Literature
ISSN 0022-0515 (Print) | ISSN 2328-8175 (Online)
Artificial Intelligence–Powered (Finance) Scholarship
Journal of Economic Literature
(pp. 5–37)
Abstract
This paper describes a process for generating academic papers using large language models (LLMs) and demonstrates this process's efficacy by producing hundreds of complete papers on stock return predictability, a topic well-suited for our illustration. After mining over 30,000 potential return predictors from accounting data, we generate template reports for 95 signals passing rigorous criteria from the Novy-Marx and Velikov (2024) Assaying Anomalies protocol. These templates detail signal performance predicting returns using a wide array of tests and benchmark performance against more than 200 documented anomalies. Finally, for each template we use state-of-the-art LLMs to generate multiple complete versions of academic papers with distinct theoretical justifications for the observed return predictability, incorporating citations to literature supporting their respective claims. This experiment illustrates the potential of artificial intelligence (AI) for enhancing financial research efficiency, but also serves as a cautionary tale, illustrating how it can be abused to industrialize hypothesizing after results are known (HARKing).Citation
Novy-Marx, Robert, and Mihail Velikov. 2026. "Artificial Intelligence–Powered (Finance) Scholarship." Journal of Economic Literature 64 (1): 5–37. DOI: 10.1257/jel.20251821Additional Materials
JEL Classification
- C12 Hypothesis Testing: General
- C45 Neural Networks and Related Topics
- G12 Asset Pricing; Trading Volume; Bond Interest Rates
- G17 Financial Forecasting and Simulation