Uncalibrated Models Can Improve Human-AI Collaboration. (arXiv:2202.05983v2 [cs.AI] UPDATED)

In many practical applications of AI, an AI model is used as a decision aid
for human users. The AI provides advice that a human (sometimes) incorporates
into their decision-making process. The AI advice is often presented with some
measure of "confidence" that the human can use to calibrate how much they
depend on or trust the advice. In this paper, we demonstrate that human-AI
performance can be improved by calibrating this confidence to the humans using
the advice. In …

ai ai collaboration arxiv collaboration human