A two-stage local LLM pipeline for medical CRF filling from EHR notes achieves macro-F1 of 0.55 on the CL4Health 2026 English test track using few-shot in-context learning without fine-tuning.
Converting Annotated Clinical Cases into Structured Case Report Forms
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
-
sebis at CRF Filling 2026: A Two-Stage Local LLM Pipeline for Medical CRF Filling
A two-stage local LLM pipeline for medical CRF filling from EHR notes achieves macro-F1 of 0.55 on the CL4Health 2026 English test track using few-shot in-context learning without fine-tuning.