Chiranjeevi Vantaku

RADAR: A Prototype for Grounding Large Language Model Consult Support in an ACR-Structured Appropriateness Knowledge Base with Citation Validation and Abstention.

Large language models (LLMs) answer medical questions fluently but fabricate statements and citations too often to be trusted unaided at the point of care. We describe RADAR (Radiology Appropriateness Decision and Advisory Resource), a prototype retrieval-augmented consult-support pipeline that grounds an LLM in a know...