sebis at CRF Filling 2026: A Two-Stage Local LLM Pipeline for Medical CRF Filling

Katharina Sommer, Tristan Till, Florian Matthes


Abstract
The extraction of structured clinical information from unstructured EHR notes is a persistent bottleneck in healthcare informatics. While large language models (LLMs) offer high performance, their deployment in clinical settings is hindered by privacy risks, inference costs, and the tendency to hallucinate beyond textual evidence. We address these challenges for the CL4Health 2026 Case Report Form (CRF) filling task by proposing a fully local, domain-adapted pipeline using the MedGemma-27B model. Our two-stage architecture, which separates binary presence classification from value extraction, enforces strict adherence to textual evidence and ensures deterministic outputs for negated, uncertain, or unknown states. By leveraging item-specific, few-shot in-context learning without external API calls or fine-tuning, our approach achieves a macro-F1 score of 0.55 on the official English test track. This result secures second place among all locally-hosted, open-source submissions. Our work demonstrates that privacy-preserving, on-premise LLM pipelines can achieve near-competitive performance with proprietary frontier models, providing a practical, data-sovereign framework for clinical NLP.
Anthology ID:
2026.cl4health-1.37
Volume:
Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Deepak Gupta, Paul Thompson, Sophia Ananiadou, Dina Demner-Fushman
Venues:
CL4Health | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
402–411
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-cl4health-37
DOI:
10.63317/2prmobstjfcg
Bibkey:
Cite (ACL):
Katharina Sommer, Tristan Till, and Florian Matthes. 2026. sebis at CRF Filling 2026: A Two-Stage Local LLM Pipeline for Medical CRF Filling. In Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026, pages 402–411, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
sebis at CRF Filling 2026: A Two-Stage Local LLM Pipeline for Medical CRF Filling (Sommer et al., CL4Health 2026)
Copy Citation: