ChatGPT vs. Students: AI Bot Performs Worse Than Students at Accounting Exams
OpenAI's chatbot, ChatGPT, was recently made available to the public for testing. Researchers from Brigham Young University (BYU), US, and 186 other universities wanted to know how the technology would fare on accounting exams.
The researchers found that despite ChatGPT's "impressive" performance, students fared better on accounting exams than the AI bot. In the researchers' accounting exam, students scored an overall average of 76.7 percent, compared to ChatGPT's score of 47.4 percent.
ChatGPT was found to perform worse on tax, financial, and managerial assessments compared to accounting information systems (AIS) and auditing, possibly due to the mathematical processes required for the latter type of questions. The AI bot struggled with short-answer questions and higher-order questions, sometimes providing descriptions for incorrect answers or answering the same question in different ways.
Although ChatGPT was found to do better on true/false questions and multiple-choice questions, the AI bot sometimes made up facts and provided nonsensical mathematical errors such as adding two numbers in a subtraction problem or dividing numbers incorrectly.
The researchers recruited 327 co-authors from 186 educational institutions in 14 countries to contribute 25,181 classroom accounting exam questions. They also fed another 2,268 textbook test bank questions to ChatGPT.
The researchers noted that ChatGPT's performance is a game-changer that will change the way everyone teaches and learns for the better. However, the ongoing debate about how models like ChatGPT should factor into education remains intense.
Follow Gadgets 360 on Twitter, Facebook, and Google News for the latest tech news and reviews. Subscribe to our YouTube channel for the latest videos on gadgets and tech.
