Keywords

artificial intelligence, text generators, chatbots, ChatGPT, accounting education

Abstract

This study evaluates the capabilities of ChatGPT models 3.5 and 4 to provide solutions to eight educational accounting cases. We find that ChatGPT’s ability to provide accurate solutions varies depending on the type of case requirement and topical area of accounting, with better performance on tasks requiring elements that require explanation, application of rules, and ethical evaluation. However, ChatGPT performs poorly on tasks that require financial statement creation, journal entries, or software use. Our study also finds that detection tools provided by ChatGPT's developer are ineffective in identifying text created by Artificial Intelligence Text Generators (AITG). We suggest ways in which instructors can develop and structure assignments to reduce the effectiveness of AITGs in subverting the learning process, and discuss ways in which AITGs can be incorporated into assignment requirements to help students attain, desired educational outcomes.

Original Publication Citation

Cheng, X., R. Dunn, T. Holt, K. Inger, J. G. Jenkins, J. Jones, J. Long, T. Loraas, M. Mathis, J. Stanley, and D. A. Wood. 2024. Artificial intelligence’s capabilities, limitations, and impact on accounting education: Investigating ChatGPT’s performance on educational accounting cases. Issues in Accounting Education, 39 (2): 23-47. DOI: 10.2308/ISSUES-2023-032.

Document Type

Peer-Reviewed Article

Publication Date

2024

Publisher

Issues in Accounting Education

Language

English

College

Marriott School of Business

Department

Accountancy

University Standing at Time of Publication

Full Professor

Download

Included in

Accounting Commons

Share

COinS