Optimizing Delegation in Collaborative Human-AI Hybrid Teams

A Fuchs, A Passarella, M Conti - arXiv preprint arXiv:2402.05605, 2024 - arxiv.org
When humans and autonomous systems operate together as what we refer to as a hybrid
team, we of course wish to ensure the team operates successfully and effectively. We refer to …

Towards Human-AI Complementarity with Predictions Sets

G De Toni, N Okati, S Thejaswi, E Straitouri… - arXiv preprint arXiv …, 2024 - arxiv.org
Decision support systems based on prediction sets have proven to be effective at helping
human experts solve classification tasks. Rather than providing single-label predictions …

Optimizing Risk-averse Human-AI Hybrid Teams

A Fuchs, A Passarella, M Conti - arXiv preprint arXiv:2403.08386, 2024 - arxiv.org
We anticipate increased instances of humans and AI systems working together in what we
refer to as a hybrid team. The increase in collaboration is expected as AI systems gain …

Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets

E Straitouri, S Thejaswi, MG Rodriguez - arXiv preprint arXiv:2406.06671, 2024 - arxiv.org
Decision support systems based on prediction sets help humans solve multiclass
classification tasks by narrowing down the set of potential label values to a subset of them …