WisPerMed at ArchEHR-QA 2026: Retrieval-Augmented Prompting for Grounded EHR Question Answering

Jan-Henning Büns, Tabea Margareta Grace Pakull, Hendrik Damm, Bohao Chu, Christoph M. Friedrich, Felix Nensa, Elisabeth Livingstone, Peter A. Horn, Norbert Fuhr


Abstract
ArchEHR-QA is a grounded question-answering (QA) task for electronic health records (EHRs) comprising four subtasks: (1) question rewriting, (2) evidence identification, (3) grounded answer generation, and (4) answer-evidence alignment. In this work, we present a modular pipeline centered on retrieval-augmented generation (RAG). For Subtask 1, RAG few-shot prompting outperformed both PEFT and prompt-only baselines on the development set; however, Claude few-shot proved substantially more robust on the test set, ranking 6th out of 13 participating teams (score: 26.94). For Subtask 2, a union ensemble of open-weight LLMs (GPT-OSS-120B and Qwen3-30B-A3B) achieved a 56.7 micro-F1, rivaling the proprietary Claude Opus 4.6 while demonstrating higher recall (53.6). For Subtask 3, our RAG few-shot approach using Claude Opus 4.5 achieved the 1st place out of 13 participating teams (score: 36.33). Finally, for Subtask 4, a zero-shot Claude Opus 4.6 configuration ranked 2nd out of 16 participating teams (score: 81.3).
Anthology ID:
2026.cl4health-1.42
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:
455–468
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-cl4health-42
DOI:
10.63317/5bb4gnhkbqjq
Bibkey:
Cite (ACL):
Jan-Henning Büns, Tabea Margareta Grace Pakull, Hendrik Damm, Bohao Chu, Christoph M. Friedrich, Felix Nensa, Elisabeth Livingstone, Peter A. Horn, and Norbert Fuhr. 2026. WisPerMed at ArchEHR-QA 2026: Retrieval-Augmented Prompting for Grounded EHR Question Answering. In Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026, pages 455–468, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
WisPerMed at ArchEHR-QA 2026: Retrieval-Augmented Prompting for Grounded EHR Question Answering (Büns et al., CL4Health 2026)
Copy Citation: