Template-type: ReDIF-Paper 1.0
Author-Name: Francesco Audrino
Author-Name-First: Francesco
Author-Name-Last: Audrino
Author-Name: Jessica Gentner
Author-Name-First: Jessica
Author-Name-Last: Gentner
Author-Person: pge381
Author-Name: Simon Stalder
Author-Name-First: Simon
Author-Name-Last: Stalder
Author-Person: pst1035
Title: Quantifying uncertainty: a new era of measurement  through large language models
Abstract: This paper presents an innovative method for measuring uncertainty via large language models (LLMs), which offer greater precision and contextual sensitivity than the conventional methods used to construct prominent uncertainty indices. By analysing newspaper texts with state-of-the-art LLMs, our approach captures nuances often missed by conventional methods. We develop indices for various types of uncertainty, including geopolitical risk, economic policy, monetary policy, and financial market uncertainty. Our findings show that shocks to these LLM-based indices exhibit stronger associations with macroeconomic variables, shifts in investor behaviour, and asset return variations than conventional indices, underscoring their potential for more accurately reflecting uncertainty.

Length: 54 pages
Creation-Date: 2024
Contact-Email: forschung@snb.ch
File-URL: https://www.snb.ch/en/publications/research/working-papers/2024/working_paper_2024_12
File-Format: text/html
Number: 2024-12
Classification-JEL: C45, C55, E44, G12
Keywords: Uncertainty measurement, Large language models, Economic policy, Geopolitical risk, Monetary policy, Financial markets
Handle: RePEc:snb:snbwpa:2024-12