Few-shot prompted LLMs reach macro-F1 0.475 on four-class patient inquiry triage from HealthCareMagic-100K, modestly above BioBERT baseline of 0.378 with overlapping confidence intervals, supporting selective human review but not autonomous use.
Bioinformatics, 36(4):1234–1240
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Few-Shot Large Language Models for Actionable Triage Categorization of Online Patient Inquiries
Few-shot prompted LLMs reach macro-F1 0.475 on four-class patient inquiry triage from HealthCareMagic-100K, modestly above BioBERT baseline of 0.378 with overlapping confidence intervals, supporting selective human review but not autonomous use.