Lisa Stump

Multi-model assurance analysis showing large language models are highly vulnerable to adversarial hallucination attacks during clinical decision support

2025 · 40 Zit. · Communications Medicine

Orchestrated multi agents sustain accuracy under clinical-scale workloads compared to a single agent

2025 · 2 Zit. · medRxiv

Orchestrated multi agents sustain accuracy under clinical-scale workloads compared to a single agent

2026 · 0 Zit. · npj Health Systems