The ChatGPT Artificial Intelligence Chatbot: How Well Does It Answer Accounting Assessment Questions?

Wood, DA Achhpilia, MP Adams, MT Aghazadeh, S Akinyele, K Akpan, M Allee, KD Allen, AM Almer, ED Ames, D Arity, V Barr-Pulliam, D Basoglu, KA Belnap, A Bentley, JW Berg, T Berglund, NR Berry, E Bhandari, A Bhuyan, MNH Black, PW Blondeel, E Bond, D ORCID badge Bonrath, A Borthick, AF Boyle, ES Bradford, M Brandon, DM Brazel, JF Brockbank, BG Burger, M Byzalov, D Cannon, JN Caro, C Carr, AH Cathey, J Cating, R Charron, K Chavez, S Chen, J Chen, JC Chen, JW Cheng, C Cheng, X Christensen, BE Church, KS Cicone, NJ Constance, P Cooper, LA Correia, CL Coyne, J Cram, WA Curtis, A Daigle, RJ Dannemiller, S Davenport, SA Dawson, GS Meyst, KJLD Dell, S Demirkan, S Denison, CA Desai, H Desimone, S Diehl, LM Dimes, R Dong, B Donnelly, A du Pon, A Duan, HK Duffey, A Dunn, RT Durkin, MP Dzuranin, AC Eberle, RM Ege, MS El Mahdy, D Esplin, A Eulerich, M Everaert, P Farah, N Farish, L Favere-Marchesi, M Fayard, D Filosa, JR Ford, M Franz, DR Fulmer, BP Fulmer, S Furner, ZZ Gantman, S Garner, S Garrett, J Geng, X Golden, J Goldman, W Gomez, J Gooley, M Granitto, SP Green, KY Greenman, CL Gupta, G Guymon, RN Hale, K Harper, CJ Hartt, SA Hawk, H Hawkins, SR Hawkins, EM Hay, DC Heinzelmann, R Henderson, CD Hendricks, BE Heninger, WG Hill, MS Holden, N Holderness, DK Holt, TP Hoopes, JL Hsieh, S-F Huang, F Huang, H-W Huang, T-C Huels, BW Hunter, K Hurley, PJ Inger, K Islam, S Ison, I Issa, H Jackson, AB Jackson, SC Janvrin, DJ Jimenez, PD Johanson, D Judd, JS Kawada, BS Kelton, AS Kern, S Kerr, JN Keune, MB Kim, MHJ Knox, BD Kogan, G Kotb, A Krane, R Kremin, J Krieg, KS Kugel, J Kulset, EM Kuruppu, C Laduca, G Lamberton, BA Lamboy-Ruiz, MA Lang, B Larocque, SA Larson, MP Lawson, BP Lawson, JG Lee, L Lenk, MM Li-Kuehne, M Liljegren, J Lin, Y-H Liu, W-P Liu, Z Lock, B Long, JH Loraas, T Lowensohn, S Loy, TR Lyngstadaas, H Maas, W Macgregor, JE Madsen, DO Malone, CL Margolin, M Marshall, ME Martin, RM Mpofu, CM Mccoy, C Mcguigan, NC Mcswain, DN Meckfessel, MD Mellon, MJ Melton, OS Mercado, JM Mitsuda, S Modugu, K Moehrle, S Chaghervand, AM Mof, K Moon, JS Muehlmann, B Murray, J Mwaungulu, ES Myers, N Naegle, JC Ndicu, MJ Nelson, AS Nguyen, AL Niederko, T Nikbakht, E O'Brien, AD Ogunade, KM O'Leary, D Oler, MJ Oler, DK Olsen, KJ Otalor, JI Outlaw, KW Ozlanski, ME Parlier, J Paterson, JS Pearson, CA Petersen, MJ Petra, ST Pickard, MD Pickerd, J Pinsker, R Plante, C Plec, JM Iii, RAP Quick, LA Raedy, J Raschke, R Ravenscraft, J Richardson, V Rixom, BA Robertson, JF Rock, I Romney, MA Rozario, A Ruff, MF Rupley, K Saeedi, A Saiewitz, A Salzsieder, LW Sarkar, S Saulls, M Scanlan, TA Schaefer, TJ Schaupp, D Schneider, GP Seebeck, A Sellers, RD Seto, SC Sevel, R-L Shan, Y Sherwood, MG Singorahardjo, M Skaftadottir, HK Skomra, J Smith, JL Smith, DO Smith, J Snow, MC Sommerfeldt, RD Sorensen, KB Sorensen, TL Spieler, AC Stallings, MA Stallings, L Stancill, A Stanley, JD Stefaniak, CM Stephens, NM Stewart, BW Stratopoulos, TC Street, DA Subedi, M Summers, SL Sundkvist, CH Synn, C Tadesse, A Tapis, GP Tassin, K Taylor, S Teal, M Teeter, R Tharapos, M Theis, JC Thomas, J Thompson, KS Thornock, TA Tietz, W Travalent, AM Trinkle, BS Truelson, JM Turner, MC Vagner, B Vakilzadeh, H Geest, JVD Pelt, VV Vandervelde, SD Vega, J Vera-Mun, S Villanueva, B Vincent, NE Wagener, M Walton, S Warne, RC V. Watanabe, O Watson, D Watson, MW Weber, J Weirich, T West, AN Wilford, AL Wilson, AB Winrow, B Winrow, T Winrow, TS Wiseman, D Witte, AL Wood, BD Wood, J Woolley, D Wright, NS Wu, J Xiong, XG Yatsenko, D Yazzie, CE Young, GM Zhang, CA Zimmerman, AB Zoet, E
Publisher:
AMER ACCOUNTING ASSOC
Publication Type:
Journal Article
Citation:
ISSUES IN ACCOUNTING EDUCATION, 2023, 38, (4), pp. 81-108
Issue Date:
2023-11
Filename Description Size
retrieve (16).pdfPublished version1.18 MB
Adobe PDF
Full metadata record
ABSTRACT ChatGPT, a language-learning model chatbot, has garnered considerable attention for its ability to respond to users’ questions. Using data from 14 countries and 186 institutions, we compare ChatGPT and student performance for 28,085 questions from accounting assessments and textbook test banks. As of January 2023, ChatGPT provides correct answers for 56.5 percent of questions and partially correct answers for an additional 9.4 percent of questions. When considering point values for questions, students significantly outperform ChatGPT with a 76.7 percent average on assessments compared to 47.5 percent for ChatGPT if no partial credit is awarded and 56.5 percent if partial credit is awarded. Still, ChatGPT performs better than the student average for 15.8 percent of assessments when we include partial credit. We provide evidence of how ChatGPT performs on different question types, accounting topics, class levels, open/closed assessments, and test bank questions. We also discuss implications for accounting education and research.
Please use this identifier to cite or link to this item: