MPD²-Router is a dual-head deferral router that uses mask-aware Gumbel-sigmoid gating, asymmetric cost-sensitive training, and rank-majorization regularization to lower clinical cost and raise MCC versus AI-only baselines while balancing expert utilization across three glaucoma cohorts.
Cost-sensitive learning to defer to multiple experts with workload constraints.arXiv preprint arXiv:2403.06906
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Human oversight for LLM agent actions is capacity-limited by subjective disagreement (kappa 0.52) and fatigue, producing an inverted-U safety curve and vulnerability to flooding attacks in a modeling study.
citing papers explorer
-
MPD$^2$-Router: Mask-aware Multi-expert Prior-regularized Dual-head Deferral Router in Glaucoma Screening and Diagnosis
MPD²-Router is a dual-head deferral router that uses mask-aware Gumbel-sigmoid gating, asymmetric cost-sensitive training, and rank-majorization regularization to lower clinical cost and raise MCC versus AI-only baselines while balancing expert utilization across three glaucoma cohorts.
-
Oversight Has a Capacity: Calibrating Agent Guards to a Subjective, Fatiguing Human
Human oversight for LLM agent actions is capacity-limited by subjective disagreement (kappa 0.52) and fatigue, producing an inverted-U safety curve and vulnerability to flooding attacks in a modeling study.