Financing
Jan 21, 2026
The Economic Logic of Large Language Models
We show that LLMs can effectively extrapolate from disparate domains of knowledge to reason through economic relationships, and that this may have advantages over narrower statistical models. Fundamentally, large language models (LLMs) and numerical models both learn patterns in training data. However, while traditional models rely on narrowly curated datasets, LLMs can extrapolate patterns across disparate domains of knowledge. In new research, we explore whether this ability is valuable for ...
1. Peter L. Bernstein Award for Best Article in an Institutional Investor Journal in 2013; Bernstein-Fabozzi/Jacobs-Levy Award for Outstanding Article in the Journal of Portfolio Management in 2006, 2009, 2011, 2013 (2), 2014, 2015, 2016, 2021; Graham & Dodd Scroll Award for article in the Financial Analysts Journal in 2002 and 2010. Roger F. Murray First Prize for Research Presented at the Q Group Conference in 2012, 2021, 2023. Harry M. Markowitz Award for Best Paper in the Journal of Investment Management in 2022, 2023. Doriot Award for Best Private Equity Research Paper in 2022.