Researcher ORCID Identifier

0000-0002-5173-2741

Document Type

Article

Publication Date

Spring 5-2024

Abstract

ChatGPT and other large language models (LLMs) do not understand the text they input and output. When three prominent LLMs were tested with 11 financial-decision prompts, the LLM responses were seemingly authoritative but riddled with arithmetic and critical-thinking mistakes. Financial planners are unlikely to be replaced by LLMs anytime soon.

Comments

Originally published in Journal of Financial Planning, Volume 37, No. 5. For more information about the journal, please visit https://www.financialplanningassociation.org/about.

Terms of Use & License Information

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Included in

Econometrics Commons

Share

COinS