Back

Representation Before Retrieval: Structured Patient Artifacts Reduce Hallucination in Clinical AI Systems

2026-02-16 health informatics Title + abstract only
View on medRxiv
Show abstract

BackgroundLarge language models show promise for clinical decision support, yet their propensity for hallucination--generating plausible but unsupported claims--poses sub-stantial patient safety risks. Retrieval-augmented generation (RAG) is widely assumed to mitigate this problem by grounding outputs in retrieved documents, but this assumption remains inadequately tested in clinical contexts where information density, temporal complexity, and safety stakes are uniquely high. MethodsWe develope...

Predicted journal destinations