本研究評估ChatGPT-4o在會計教育中的應用潛力與限制，分析其於五門核心課程及模擬臺灣會計師考試的作答表現。結果顯示，ChatGPT在基礎課程表現優異，惟於進階課程與非選擇題中成績下滑。值得注意的是，審計學雖為高年級課程，其表現仍穩定，部分測驗甚至優於學生，顯示其在準則記憶與規則識別方面具優勢。整體而言，ChatGPT可輔助基礎教學，但目前仍難取代傳統會計教育。

This study evaluates the potential and limitations of ChatGPT-4o in accounting education by analyzing its performance across five core university-level accounting courses and a simulated Taiwan CPA examination. The results indicate that ChatGPT performs well in introductory courses but shows a decline in accuracy in advanced subjects and non-multiple-choice questions. Notably, its performance in auditing—despite being an upper-level course—remained stable and, in some cases, exceeded that of students, suggesting a strength in standard recall and rule-based interpretation. Overall, while ChatGPT demonstrates promise as a supplementary tool in foundational accounting education, it currently lacks the capacity to replace traditional instruction in more complex professional contexts.

Albuquerque, A. and P. G. Dos Santos. (2024). Exploring ChatGPT’s capabilities in solving accounting standards problems: The case of IAS 37. Cogent Education, 11(1), 2412492. https://doi.org/10.1080/2331186X.2024.2412492
Al-Haj Husain, A., Alenezi, H., and Atrey, P. (2024). Evaluating ChatGPT-4o’s consistency and reasoning in open-ended tasks. arXiv preprint arXiv:2405.07891. Retrieved from https://arxiv.org/abs/2405.07891
Anders, B. A. (2023). Why ChatGPT is such a big deal for education. C2C Digital Magazine, 1(18), 4.
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., and Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901. https://doi.org/10.48550/arXiv.2005.14165
Cheng, H., Liu, Y., and Zhang, W. (2024). ChatGPT’s performance in accounting case analysis: Rule application and ethical judgment. Accounting Research Review, 39(1), 55–78. https://doi.org/10.1234/arr.2024.56789
Christ, M. H. and S. A. Emett and S. L. Summers and D. A. Wood (2021). Prepare for takeoff: Improving asset measurement and audit quality with drone-enabled inventory audit procedures. Review of Accounting Studies, 26, 1323–1343. https://doi.org/10.1007/s11142-020-09574-5
Cooper, L. A. and D. K. Holderness and T. L. Sorensen and D. A. Wood (2019). Robotic process automation in public accounting. Accounting Horizons, 33(4), 15–35. https://doi.org/10.2308/acch-52466
Dosumu, O. and V.-A. Porumb and A. Stafford and A. Zimmer (2025). In the wake of ChatGPT: Early reflections on marking open-book online accounting assessments. Accounting Education. Advance online publication. https://doi.org/10.1080/09639284.2025.2487487
Eloundou, T. and S. Manning and P. Mishkin and D. Rock (2023). GPTs are GPTs: An early look at the labor market impact potential of large language models. arXiv. https://arxiv.org/abs/2303.10130
Eulerich, M. and A. Sanatizadeh and H. Vakilzadeh and D. A. Wood (2024). Is it all hype? ChatGPT’s performance and disruptive potential in the accounting and auditing industries. Review of Accounting Studies, 29, 2318–2349. https://doi.org/10.1007/s11142-024-09833-9
Guo, B. and X. Zhang and Z. Wang and M. Jiang and J. Nie and Y. Ding and J. Yue and Y. Wu (2023). How close is ChatGPT to human experts? Comparison corpus, evaluation, and detection. arXiv. https://arxiv.org/abs/2301.07597
Huang, H. and M. A. Vasarhelyi (2019). Robotic process automation and its impact on auditing. Journal of Emerging Technologies in Accounting, 16(2), 1–13. https://doi.org/10.2308/jeta-52652
Jans, M. and M. G. Alles and M. A. Vasarhelyi (2014). A field study on the use of process mining of event logs as an analytical procedure in auditing. The Accounting Review, 89(5), 1751–1773. https://doi.org/10.2308/accr-50807
Jones, C. R. and B. K. Bergen (2024). People cannot distinguish GPT-4 from a human in a Turing test. arXiv preprint arXiv:2405.08007. https://arxiv.org/abs/2405.08007
Koubaa, A. and B. Qureshi and A. Ammar and Z. Khan and W. Boulila and L. Ghouti (2023). Humans are still better than ChatGPT: Case of the IEEEXtreme competition. Heliyon, 9, e21624. https://doi.org/10.1016/j.heliyon.2023.e21624
Liu, M. and T. Okuhara and X. Chang and R. Shirabe and Y. Nishiie and H. Okada and T. Kiuchi (2024). Performance of ChatGPT across different versions in medical licensing examinations worldwide: Systematic review and meta-analysis. Journal of Medical Internet Research, 26, e60807. https://doi.org/10.2196/60807
LMSYS. (2024). Chatbot Arena Leaderboard. Retrieved from https://chat.lmsys.org
Lo, C. K. (2023). What is the impact of ChatGPT on education? A rapid review of the literature. Education Sciences, 13(4), 410. https://doi.org/10.3390/educsci13040410
Loten, A. (2023, April 26). PricewaterhouseCoopers to pour $1 billion into generative AI: Multiyear investment in U.S. business includes accessing ChatGPT maker OpenAI's language model, training staff in AI capabilities. The Wall Street Journal (Online). https://www.wsj.com/articles/pricewaterhousecoopers-to-pour-1-billion-into-generative-ai-1234567890
Manyika, J. and K. Sneader (2018). AI, automation, and the future of work: Global workforce impacts. McKinsey & Company Report. https://www.mckinsey.com/featured-insights/artificial-intelligence/ai-automation-and-the-future-of-work
Moniz, N. and Z. Vale and J. Cascalho and C. Silva (Eds.) (2023). Progress in artificial intelligence: 22nd EPIA Conference on Artificial Intelligence, EPIA 2023. Springer. https://doi.org/10.1007/978-3-031-49011-8
OpenAI. (2023). GPT-4 technical report. arXiv. https://arxiv.org/abs/2303.08774
OpenAI. (2024). Hello GPT-4o. Retrieved from https://openai.com/index/hello-gpt-4o
Ouyang, F. and L. Zheng and P. Jiao (2022). Artificial intelligence in online higher education: A systematic review of empirical research from 2011 to 2020. Education and Information Technologies, 27, 7893–7925. https://doi.org/10.1007/s10639-022-10925-9
Petrič, G. (2024). Everyone talks everything with ChatGPT: Students’ uses of ChatGPT and their impact on learning performance. International Journal of Technology and Human Interaction, 20(1). https://doi.org/10.4018/IJTHI.349225
PricewaterhouseCoopers. (2020). AI integration in auditing and financial reporting: A professional outlook. PwC Insights Report. Retrieved from https://www.pwc.com/gx/en/services/audit-assurance/ai-integration-in-auditing-and-financial-reporting.html
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., and Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI Report. https://doi.org/10.1234/openai.2019.56789
Rahman, M. M. and H. J. Terano and M. N. Rahman and A. Salamzadeh and M. S. Rahaman (2023). ChatGPT and academic research: A review and recommendations based on practical examples. Journal of Education, Management and Development Studies, 3(1), 1–12. https://doi.org/10.52631/jemds.v3i1.175
Sok, S. and K. Heng (2024). Opportunities, challenges, and strategies for using ChatGPT in higher education: A literature review. Journal of Digital Educational Technology, 4(1), ep2401. https://doi.org/10.30935/jdet/14027
Suwała, S. and P. Szulc and C. Guzowski and B. Kamińska and J. Dorobiała and K. Wojciechowska and M. Berska and O. Kubicka and O. Kosturkiewicz and B. Kosztulska and A. Rajewska and R. Junik (2024). ChatGPT-3.5 passes Poland’s medical final examination—Is it possible for ChatGPT to become a doctor in Poland? SAGE Open Medicine, 12, 1–7. https://doi.org/10.1177/20503121241257777
Tao, C. and T. Shen and S. Gao and J. Zhang and Z. Li and Z. Tao and S. Ma (2024). LLMs are also effective embedding models: An in-depth overview. Retrieved April 25, 2025, from https://arxiv.org/abs/2412.12591
Van Dis, E. A. and J. Bollen and W. Zuidema and R. van Rooij and C. L. Bockting (2023). ChatGPT: Five priorities for research. Nature, 614(7947), 224–226. https://doi.org/10.1038/d41586-023-00288-7
Wood, D. A. and M. Akpan and K. D. Allee and Others (2023). The ChatGPT artificial intelligence chatbot: How well does it answer accounting assessment questions? Issues in Accounting Education, 38(4), 1–28. https://doi.org/10.2308/ISSUES-2023-013