TechDigits

Tech news
Thursday, Jun 08, 2023

Students Beat ChatGPT At This Exam, Score 76%, Compared To Chatbot's 47%

Students Beat ChatGPT At This Exam, Score 76%, Compared To Chatbot's 47%

Despite this, they said that ChatGPT's performance was "impressive" and that it was a "game changer that will change the way everyone teaches and learns - for the better."
Researchers found students to have fared better at accounting exams than ChatGPT, OpenAI's chatbot product.

Despite this, they said that ChatGPT's performance was "impressive" and that it was a "game changer that will change the way everyone teaches and learns - for the better."

The researchers from Brigham Young University (BYU), US, and 186 other universities wanted to know how OpenAI's technology would fare on accounting exams. They have published their findings in the journal Issues in Accounting Education.

In the researchers' accounting exam, students scored an overall average of 76.7 per cent, compared to ChatGPT's score of 47.4 per cent.

While in 11.3 per cent of the questions, ChatGPT was found to score higher than the student average, doing particularly well on accounting information systems (AIS) and auditing, the AI bot was found to perform worse on tax, financial, and managerial assessments. Researchers think this could possibly be because ChatGPT struggled with the mathematical processes required for the latter type.

The AI bot, which uses machine learning to generate natural language text, was further found to do better on true/false questions (68.7 per cent correct) and multiple-choice questions (59.5 per cent), but struggled with short-answer questions (between 28.7 and 39.1 per cent).

In general, the researchers said that higher-order questions were harder for ChatGPT to answer. In fact, sometimes ChatGPT was found to provide authoritative written descriptions for incorrect answers, or answer the same question different ways.

They also found that ChatGPT often provided explanations for its answers, even if they were incorrect. Other times, it went on to select the wrong multiple-choice answer, despite providing accurate descriptions.

Researchers importantly noted that ChatGPT sometimes made up facts. For example, when providing a reference, it generated a real-looking reference that was completely fabricated. The work and sometimes the authors did not even exist.

The bot was seen to also make nonsensical mathematical errors such as adding two numbers in a subtraction problem, or dividing numbers incorrectly.

Wanting to add to the intense ongoing debate about how how models like ChatGPT should factor into education, lead study author David Wood, a BYU professor of accounting, decided to recruit as many professors as possible to see how the AI fared against actual university accounting students.

His co-author recruiting pitch on social media exploded: 327 co-authors from 186 educational institutions in 14 countries participated in the research, contributing 25,181 classroom accounting exam questions.

They also recruited undergraduate BYU students to feed another 2,268 textbook test bank questions to ChatGPT. The questions covered AIS, auditing, financial accounting, managerial accounting and tax, and varied in difficulty and type (true/false, multiple choice, short answer).
AI Disclaimer: An advanced artificial intelligence (AI) system generated the content of this page on its own. This innovative technology conducts extensive research from a variety of reliable sources, performs rigorous fact-checking and verification, cleans up and balances biased or manipulated content, and presents a minimal factual summary that is just enough yet essential for you to function as an informed and educated citizen. Please keep in mind, however, that this system is an evolving technology, and as a result, the article may contain accidental inaccuracies or errors. We urge you to help us improve our site by reporting any inaccuracies you find using the "Contact Us" link at the bottom of this page. Your helpful feedback helps us improve our system and deliver more precise content. When you find an article of interest here, please look for the full and extensive coverage of this topic in traditional news sources, as they are written by professional journalists that we try to support, not replace. We appreciate your understanding and assistance.
Newsletter

Related Articles

TechDigits
Close
0:00
0:00
Nvidia Joins Tech Giants as First Chipmaker to Reach $1 Trillion Valuation
AI ‘extinction’ should be same priority as nuclear war – experts
Prominent Hacker Forum RaidForums Suffers Substantial Data Breach
Nvidia CEO Huang says firms, individuals without AI expertise will be left behind
WPP Revolutionizes Advertising with NVIDIA's AI Powerhouse
TikTok Sues Montana Over Law Banning the App
Mobile phone giant Vodafone to cut 11,000 jobs globally over three years as new boss says its performance not good enough
Warren Buffett Sells TSMC Shares Over Concerns About Taiwan's Stability
'Godfather Of AI' Geoffrey Hinton Quits Google To Warn Of The Tech's Dangers
Vermont Man Charged with Stalking After Secretly Tracking Woman with Apple AirTag
Elon Musk Statements About Tesla Autopilot Could Be 'Deepfakes,' Lawyers Claim. Judge Evette Pennypacker Does Not Understand How Far and Advanced This Technology Became
AT&T's Successful Test of Satellite-Based Phone Call Raises Possibility of Widespread Coverage
Pulitzer Prize-winning journalist Seymour Hersh slams New York Times' pro-government stance and treatment of sources
Fox News Settles their case with Dominion Voting Systems for a staggering $787.5 MILLION
The G-7 aims to make global crypto regulations tougher
China and Brazil have signed a new deal that will allow them to trade in their own currencies, bypassing the US dollar as an intermediary
Elon Musk and Others Call for Pause on A.I., Citing ‘Profound Risks to Society’
U.S. charges FTX's Bankman-Fried with paying $40 million bribe
Fallen 'Crypto King' Who Owes Millions to Investors Was Kidnapped and Tortured
Regulators blame social media for SVB's rapid collapse: 'Complete game changer'
AOC explains why she opposes banning TikTok
Gordon Moore, a co-founder of Intel Corporation, died at 94
Donald Trump arrested – Twitter goes wild with doctored pictures
Credit Suisse's Scandalous History Resulted in an Obvious Collapse - It's time for regulators who fail to do their job to be held accountable and serve as an example by being behind bars.
Russian Hackers Preparing New Cyber Assault Against Ukraine
A brief banking situation report
Elon Musk Is Planning To Build A Town In Texas For His Employees
The Silicon Valley Bank’s collapse effect is spreading around the world, affecting startup companies across the globe
Market Chaos as USDC Loses Peg to USD after $3.3 Billion Reserves Held by Silicon Valley Bank Closed.
Banking regulators close SVB, the largest bank failure since the financial crisis
In a major snub to Downing Street's Silicon Valley dreams, UK chip giant Arm has dealt a serious blow to the government's economic strategy by opting for a US listing
It's the question on everyone's lips: could a four-day workweek be the future of employment?
Corruption and Influence Buying Uncovered in International Mainstream Media: Investigation Reveals Growing Disinformation Mercenaries
Being a Tiktoker might be expensive…
China's top tech firms, including Alibaba, Tencent, Baidu, NetEase, and JD.com, are developing their own versions of Open AI's AI-powered chatbot, ChatGPT
This shocking picture, showing how terrible is the results of the earthquake in Turkey
The desk of King Carlos Alberto of Sardinia has many secret compartments
Charlie Munger, calls for a ban on cryptocurrencies in the US, following China's lead
First generation unopened iPhone set to fetch more than $50,000 at auction.
Almost 30% of professionals say they've tried ChatGPT at work
Interpol seeks woman who ran elaborate exam cheating scam in Singapore
What is ChatGPT?
Tesla reported record profits and record revenues for 2022
Microsoft is finalising plans to become the latest technology giant to reduce its workforce during a global economic slowdown
Tesla slashes prices globally by as much as 20 percent
After Failing To Pay Office Rent, Twitter May Sell User Names
FTX fraud investigators are digging deeper into Sam Bankman-Fried's inner circle – and reportedly have ex-engineer Nishad Singh in their sights
TikTok CEO Plans to Meet European Union Regulators
U.S. Moves to Seize Robinhood Shares, Silvergate Accounts Tied to FTX
Coinbase to Pay $100 Million in Settlement With New York Regulator
×