Optimal AI recommendation policies under correlated features require an explore-then-commit structure rather than stationary policies, with NP-hard computation and a DP algorithm for finite horizons.
Explanations are a means to an end.arXiv preprint arXiv:2506.22740
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Alignment between AI and human confidence reduces regret in binary AI-assisted decision learning from Ω(√|H||B|T) to O(√|H|T log T) under perfect alignment.
citing papers explorer
-
Human Decision-Making with AI Assistance under Correlated Features
Optimal AI recommendation policies under correlated features require an explore-then-commit structure rather than stationary policies, with NP-hard computation and a DP algorithm for finite horizons.
-
Learning to Decide with AI Assistance under Human-Alignment
Alignment between AI and human confidence reduces regret in binary AI-assisted decision learning from Ω(√|H||B|T) to O(√|H|T log T) under perfect alignment.