MATRIX combines a structured safety taxonomy, an LLM hazard judge, and a patient simulator to benchmark clinical dialogue agents, claiming expert-level hazard detection and revealing weak emergency handling in current LLMs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MATRIX: Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation
MATRIX combines a structured safety taxonomy, an LLM hazard judge, and a patient simulator to benchmark clinical dialogue agents, claiming expert-level hazard detection and revealing weak emergency handling in current LLMs.