After failing in UPSC , now less number of students than students of ChatGPT have defeated ChatGPT in the exam. OpenAI's chatbot ChatGPT has recently compared the performance of the accounts exam and the performance of the students. In this, students performed better than ChatGPT, yet researchers found the performance of chatbot better. According to the research, he said that ChatGPT is a game changer that will revolutionize the way people teach and learn.
A group of researchers from Brigham Young University (BYU) and 186 other universities wanted to check the performance of OpenAI in the accounts paper. According to research, students scored an average of 76.7 per cent marks in the Accounts paper, while ChatGPT secured 47.4 marks.
ChatGPT got so many marks in the exam
This can potentially be attributed to the bot's difficulty with the mathematical calculations required for these types of questions. The AI bot uses machine learning to produce normal language text and performs better on true/false questions (68.7 percent correct) and multiple-choice questions (59.5 percent), but worse on short-answer questions (28.7 percent to) but were less accurate.
Chatgpt gave wrong answer
According to the researcher, ChatGPT found it challenging to answer higher order questions and sometimes gave wrong answers with authoritative written explanations or answered the same question in different ways.
Test the abilities of students and ChatGPT
David Wood, a BYU accounting professor, recruited several professors to test the university's accounting students and ChatGPT abilities. With the help of 327 co-authors from 186 institutions in 14 countries, he contributed over 25,000 classroom accounting questions.
The research used 2,268 textbook test bank questions from undergraduate BYU students, covering a variety of account topics and question types.
No comments:
Post a Comment