A multi-stage LLM pipeline classifies hospital staff messages by reason, with o3 reaching 78.4% weighted F1 on a 500-message labeled set.
E., Jackson, K., & DeShazo, J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
From Staff Messages to Actionable Insights: A Multi-Stage LLM Classification Framework for Healthcare Analytics
A multi-stage LLM pipeline classifies hospital staff messages by reason, with o3 reaching 78.4% weighted F1 on a 500-message labeled set.