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). ( JEL C12, C45, G12, G17)
Novy‐Marx et al. (Thu,) studied this question.