GigitAI at ArchEHR-QA 2026: Prompting Strategies and Constitutional AI for Clinical Question Answering

Saran Krishnasamy, Inez Wihardjo


Abstract
Answering patient questions from electronic health records requires identifying relevant evidence in lengthy clinical notes and generating faithful, patient-friendly answers. We present a systematic study of LLM prompting strategies for both tasks, evaluating 21 evidence identification methods and 13 answer generation methods across 7 language models. For evidence identification, we find that LLM prompting outperforms traditional retrieval (BM25, SBERT, BioLinkBERT) by 19 F1 points, and that prompt framing alone controls precision–recall trade-offs: inclusive framing achieves 90% recall on dev while balanced framing reaches 67% precision. For answer generation, we introduce a Constitutional AI pipeline that critiques and revises answers against five clinical faithfulness principles, improving BLEU and ROUGE over the constrained baseline. Our analysis reveals that chain-of-thought effectiveness is strongly model-dependent, and that simple well-designed prompts outperform complex multi-step pipelines. We evaluate our approaches on the ArchEHR-QA 2026 shared task at CL4Health, achieving 58.0 F1 for evidence identification and 31.8 overall for answer generation.
Anthology ID:
2026.cl4health-1.53
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:
565–577
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-cl4health-53
DOI:
10.63317/57f49ajj4svw
Bibkey:
Cite (ACL):
Saran Krishnasamy and Inez Wihardjo. 2026. GigitAI at ArchEHR-QA 2026: Prompting Strategies and Constitutional AI for Clinical Question Answering. In Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026, pages 565–577, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
GigitAI at ArchEHR-QA 2026: Prompting Strategies and Constitutional AI for Clinical Question Answering (Krishnasamy & Wihardjo, CL4Health 2026)
Copy Citation: