Bahama Times

Tuesday, May 28, 2024

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).
Newsletter

Related Articles

Bahama Times
0:00
0:00
Close
Paper straws found to contain long-lasting and potentially toxic chemicals - study
FTX's Bankman-Fried headed for jail after judge revokes bail
Blackrock gets half a trillion dollar deal to rebuild Ukraine
Israel: Unprecedented Civil Disobedience Looms as IDF Reservists Protest Judiciary Reform
America's First New Nuclear Reactor in Nearly Seven Years Begins Operations
Southeast Asia moves closer to economic unity with new regional payments system
Today Hunter Biden’s best friend and business associate, Devon Archer, testified that Joe Biden met in Georgetown with Russian Moscow Mayor's Wife Yelena Baturina who later paid Hunter Biden $3.5 million in so called “consulting fees”
Singapore Carries Out First Execution of a Woman in Two Decades Amid Capital Punishment Debate
Google testing journalism AI. We are doing it already 2 years, and without Google biased propoganda and manipulated censorship
Unlike illegal imigrants coming by boats - US Citizens Will Need Visa To Travel To Europe in 2024
Musk announces Twitter name and logo change to X.com
The politician and the journalist lost control and started fighting on live broadcast.
The future of sports
Unveiling the Black Hole: The Mysterious Fate of EU's Aid to Ukraine
Farewell to a Music Titan: Tony Bennett, Renowned Jazz and Pop Vocalist, Passes Away at 96
Alarming Behavior Among Florida's Sharks Raises Concerns Over Possible Cocaine Exposure
Transgender Exclusion in Miss Italy Stirs Controversy Amidst Changing Global Beauty Pageant Landscape
Joe Biden admitted, in his own words, that he delivered what he promised in exchange for the $10 million bribe he received from the Ukraine Oil Company.
TikTok Takes On Spotify And Apple, Launches Own Music Service
Global Trend: Using Anti-Fake News Laws as Censorship Tools - A Deep Dive into Tunisia's Scenario
Arresting Putin During South African Visit Would Equate to War Declaration, Asserts President Ramaphosa
Hacktivist Collective Anonymous Launches 'Project Disclosure' to Unearth Information on UFOs and ETIs
Typo sends millions of US military emails to Russian ally Mali
Server Arrested For Theft After Refusing To Pay A Table's $100 Restaurant Bill When They Dined & Dashed
The Changing Face of Europe: How Mass Migration is Reshaping the Political Landscape
China Urges EU to Clarify Strategic Partnership Amid Trade Tensions
Europe is boiling: Extreme Weather Conditions Prevail Across the Continent
The Last Pour: Anchor Brewing, America's Pioneer Craft Brewer, Closes After 127 Years
Democracy not: EU's Digital Commissioner Considers Shutting Down Social Media Platforms Amid Social Unrest
Sarah Silverman and Renowned Authors Lodge Copyright Infringement Case Against OpenAI and Meta
Italian Court's Controversial Ruling on Sexual Harassment Ignites Uproar
Why Do Tech Executives Support Kennedy Jr.?
The New York Times Announces Closure of its Sports Section in Favor of The Athletic
BBC Anchor Huw Edwards Hospitalized Amid Child Sex Abuse Allegations, Family Confirms
Florida Attorney General requests Meta CEO's testimony on company's platforms' alleged facilitation of illicit activities
The Distorted Mirror of actual approval ratings: Examining the True Threat to Democracy Beyond the Persona of Putin
40,000 child slaves in Congo are forced to work in cobalt mines so we can drive electric cars.
BBC Personalities Rebuke Accusations Amidst Scandal Involving Teen Exploitation
A Swift Disappointment: Why Is Taylor Swift Bypassing Canada on Her Global Tour?
Historic Moment: Edgars Rinkevics, EU's First Openly Gay Head of State, Takes Office as Latvia's President
Bye bye democracy, human rights, freedom: French Cops Can Now Secretly Activate Phone Cameras, Microphones And GPS To Spy On Citizens
The Poor Man With Money, Mark Zuckerberg, Unveils Twitter Replica with Heavy-Handed Censorship: A New Low in Innovation?
Unilever Plummets in a $2.5 Billion Free Fall, to begin with: A Reckoning for Misuse of Corporate Power Against National Interest
Beyond the Blame Game: The Need for Nuanced Perspectives on America's Complex Reality
Twitter Targets Meta: A Tangle of Trade Secrets and Copycat Culture
The Double-Edged Sword of AI: AI is linked to layoffs in industry that created it
US Sanctions on China's Chip Industry Backfire, Prompting Self-Inflicted Blowback
Meta Copy Twitter with New App, Threads
The New French Revolution
BlackRock Bitcoin ETF Application Refiled, Naming Coinbase as ‘Surveillance-Sharing’ Partner
×