Making AI more trustworthy by making it red-flag its own doubtful answers

T2Covered by 1 source · first reported by Phys.org / ScienceDaily (tech) at 24 Sept, 14:20 UTC

Artificial intelligence models can give users the wrong answer and do so with great confidence. They can also hedge and warn that they are unsure—even when they get the answer right.

ai

Sources

• T2Making AI more trustworthy by making it red-flag its own doubtful answersPhys.org / ScienceDaily (tech)24 Sept, 14:20