RASC retrieves similar value sets to form a candidate pool then classifies codes, achieving AUROC 0.852 and F1 0.298 on a new benchmark of 11,803 VSAC sets while outperforming direct LLM generation and retrieval-only baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Retrieve, Then Classify: Corpus-Grounded Automation of Clinical Value Set Authoring
RASC retrieves similar value sets to form a candidate pool then classifies codes, achieving AUROC 0.852 and F1 0.298 on a new benchmark of 11,803 VSAC sets while outperforming direct LLM generation and retrieval-only baselines.