Verified
Should AI admit what it doesn't know?
The Independent · Published May 11, 2026, 9:00 AM UTC · Collected Oct 6, 2026, 2:22 AM UTC
Researchers at the Korea Advanced Institute of Science and Technology have developed a training method that helps AI models recognise unfamiliar topics and say "I don't know" instead of guessing. The work targets AI overconfidence — a major risk in fields like medicine and autonomous driving — since widely used chatbots are incentivised to produce plausible answers rather than admit uncertainty.
EnglishUnited KingdomEuropeResearch & ScienceTechnology & ToolsEducation & Learning