Template-Type: ReDIF-Article 1.0
Author-Name: Byeungchun Kwon
Author-Name: Taejin Park
Author-Name: Fernando Perez-Cruz
Author-Name: Phurichai Rungcharoenkitkul
Title: Large language models: a primer for economists
Abstract: Large language models (LLMs) are powerful tools for analysing textual data, with substantial untapped potential in economic and central banking applications. Vast archives of text, including policy statements, financial reports and news, offer rich opportunities for analysis. This special feature provides an accessible introduction to LLMs aimed at economists and offers applied researchers a practical walkthrough of their use. We provide a step-by-step guide on the use of LLMs covering data organisation, signal extraction, quantitative analysis and output evaluation. As an illustration, we apply the framework to analyse perceived drivers of stock market dynamics based on over 60,000 news articles between 2021 and 2023. While macroeconomic and monetary policy news are important, market sentiment also exerts substantial influence. 
Journal: BIS Quarterly Review
File-URL: http://www.bis.org/publ/qtrpdf/r_qt2412b.pdf
File-Format: Application/pdf
File-URL: http://www.bis.org/publ/qtrpdf/r_qt2412b.htm
File-Format: text/html
Year: 2024
Month: December
Classification-JEL: C55, C63, G10
Handle: RePEc:bis:bisqtr:2412b