Skeptical Chatbot: A Theory-Based Design for Judgment and Decision-Making in Auditing

Journal Contribution ResearchOnline@JCU
De Silva, Chameera;Halloluwa, Thilina;Das, Abhijit;Singh, Abhijeet;Azim, Mohammad
Abhijit Das
Abstract

Through structured prompt design and skepticism-focused training, large language models can replicate and reinforce skeptical behaviors among auditors. AI interactions grounded in the self-determination theory support deeper engagement and promote autonomy, competence, and relatedness. Techniques such as chain-of-thought prompting and SHAP/LIME visualizations make AI reasoning transparent and critical in regulated, high-stakes professional environments.

Journal

Interactions N Y

Publication Name

Interactions

Volume

33

ISBN/ISSN

1558-3449

Edition

N/A

Issue

3

Pages Count

5

Location

N/A

Publisher

Association for Computing Machinery

Publisher Url

N/A

Publisher Location

N/A

Publish Date

N/A

Url

N/A

Date

N/A

EISSN

N/A

DOI

10.1145/3793428