Medical Xpress January 11, 2025
Bob Yirka, Medical Xpress

By conducting tests under an experimental scenario, a team of medical researchers and AI specialists at NYU Langone Health has demonstrated how easy it is to taint the data pool used to train LLMs.

For their study published in the journal Nature Medicine, the group generated thousands of articles containing and inserted them into an AI and conducted general LLM queries to see how often the misinformation appeared.

Prior research and anecdotal evidence have shown that the answers given by LLMs such as ChatGPT are not always correct and, in fact, are sometimes wildly off-base. Prior research has also shown that misinformation planted intentionally on well-known internet sites can show up in generalized chatbot queries. In this...

Today's Sponsors

Venturous
Got healthcare questions? Just ask Transcarent

Today's Sponsor

Venturous

 
Topics: AI (Artificial Intelligence), Health System / Hospital, Provider, Survey / Study, Technology, Trends
The 3 most promising uses for GenAI in healthcare
OpenAI’s $40 Billion And Circle IPO: AI And Blockchain’s Revolution
The Flawed Assumption Behind AI Agents’ Decision-Making
Q&A: Researcher discusses agentic AI, expected to be the next trend in digital medicine
Generative AI Is A Crisis For Copyright Law

Share This Article