Re(Visiting) Large Language Models in Finance

55 Pages Posted: 3 Oct 2024 Last revised: 24 Jan 2025

See all articles by Eghbal Rahimikia

Eghbal Rahimikia

The University of Manchester - Alliance Manchester Business School

Felix Drinkall

University of Oxford - Oxford-Man Institute of Quantitative Finance

Date Written: September 21, 2024

Abstract

This study evaluates the effectiveness of specialised large language models (LLMs) developed for accounting and finance. Empirical analysis demonstrates that these domain-specific models, despite being nearly 50 times smaller, consistently outperform state-of-the-art general-purpose LLMs in return prediction. By pre-training the models on year-specific financial datasets from 2007 to 2023, the study also mitigates look-ahead bias, a common limitation of general-purpose LLMs. The findings highlight the critical importance of addressing look-ahead bias to ensure reliable results. Extensive robustness checks further validate the superior performance of these models.

Keywords: Natural Language Processing, Large Language Models, Asset Pricing, Return Prediction, Machine Learning

JEL Classification: G10, G11, G14, C22, C23, C45, C55, C58

Suggested Citation

Rahimikia, Eghbal and Drinkall, Felix, Re(Visiting) Large Language Models in Finance (September 21, 2024). Available at SSRN: https://ssrn.com/abstract=4963618 or http://dx.doi.org/10.2139/ssrn.4963618

Eghbal Rahimikia (Contact Author)

The University of Manchester - Alliance Manchester Business School ( email )

Booth Street West
Manchester, M15 6PB
United Kingdom

HOME PAGE: http://www.rahimikia.com

Felix Drinkall

University of Oxford - Oxford-Man Institute of Quantitative Finance ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
22,827
Abstract Views
26,192
Rank
276
PlumX Metrics