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.
Proof.Similar to Lemma A.1 Auer et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.