Uncalibrated Models Can Improve Human-AI Collaboration. (arXiv:2202.05983v3 [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 present an initial exploration
that suggests showing AI models as more confident than they actually are, even
when …

ai collaboration arxiv collaboration human