AI Prior Authorization Letters: Clinical Strengths, Admin Gaps
Explore how AI excels in clinical content but lacks administrative precision in prior authorization letters, impacting healthcare workflows.
Rigorous Explanations for Tree Ensemble Models
Discover how to generate rigorous, logically sound explanations for tree ensembles like random forests and boosted trees to boost transparency and trust.
BenchScope: Measuring Independent Signals in AI Benchmarks
Discover how BenchScope's Effective Dimensionality metric reveals independent signals and redundancy in AI benchmark scores for reliable evaluation.
Nomad: Advanced Autonomous Data Exploration System
Discover Nomad, an AI system for autonomous data exploration, generating trustworthy insights and diverse reports from complex data sources.
PSPA-Bench: Benchmark for Personalized Smartphone GUI Agents
Discover PSPA-Bench, a benchmark evaluating personalized smartphone GUI agents with 12,855+ instructions across 22 apps for real-world user workflows.