📄
Assessing the System-Instruction Vulnerabilities of Large Language Models to Malicious Conversion Into Health Disinformation Chatbots
Source page
AuthorsNatansh D. Modi, Bradley D. Menz, Abdulhalim A. Awaty
Year2025
JournalAnnals of Internal Medicine
TypeScientific Paper
Citations8
DOI10.7326/annals-24-03933