AI RESEARCH
Learning to Decide with AI Assistance under Human-Alignment
arXiv CS.AI
•
ArXi:2605.12646v1 Announce Type: cross It is widely agreed that when AI models assist decision-makers in high-stakes domains by predicting an outcome of interest, they should communicate the confidence of their predictions. However, empirical evidence suggests that decision-makers often struggle to determine when to trust a prediction based solely on this communicated confidence.