Last Update: January 15, 2023, 15:32 IST
The ChatGPT-generated abstracts went through a plagiarism checker. Reuters photo
A research team led by Catherine Gao at Northwestern University in Chicago used ChatGPT to generate artificial paper abstracts to test whether scientists could find them.
An artificial-intelligence (AI) chatbot called ChatGPT wrote convincingly fake research paper abstracts that scientists were unable to spot, a new research has revealed.
A research team led by Catherine Gao at Northwestern University in Chicago used ChatGPT to generate artificial paper abstracts to test whether scientists could find them.
According to a report in the prestigious journal Nature, the researchers asked the chatbot to write 50 medical-research abstracts based on a selection published in JAMA, The New England Journal of Medicine, The BMJ, The Lancet and Nature Medicine.
They then compared these with the original abstracts by running them through a plagiarism detector and an AI-output detector, and they asked a group of medical researchers to spot the fabricated abstracts.
ChatGPT-generated abstract through plagiarism checker: The average originality score was 100 percent, which indicates that no plagiarism was detected.
The AI-output detector saw 66 percent of the abstracts it generated. But the human reviewers didn’t do much better – they correctly identified only 68 percent of the generated abstracts and 86 percent of the actual abstracts.
According to the Nature article, they incorrectly identified 32 percent of generated essences as being genuine and 14 percent of genuine essences as being generated.
“I’m very worried,” said Sandra Wachter from the University of Oxford, who was not involved in the research.
“If we are now in a situation where experts are not able to determine what is true or not, then we lose the middleman we so desperately need to guide us through complex topics,” he was quoted as saying. Was quoted.
Microsoft-owned software company OpenAI released the tool for public use in November and it is free to use.
The report states, “Since its release, researchers have grappled with the ethical issues surrounding its use, as much of its output can be difficult to distinguish from human-written text.”
read all Latest Tech News Here
(This story has not been edited by News18 staff and is published from a syndicated news agency feed)