Daniel I. Jackson

Toward trustworthy chatbots: a protocol for red teaming for health related conversations

2026 · Scientific Reports

Health-related chatbots require safety assurance beyond factual correctness. We propose a red-teaming protocol for patient-facing AI structured around three pillars: error stratification, dual-pronged testing, and vulnerability-informed mitigation. We distinguish Document Adherence (DA) from Instruction Adherence …