@inproceedings{krishnasamy-wihardjo-2026-gigitai-archehr,
title = "{G}igit{AI} at {A}rch{EHR}-{QA} 2026: Prompting Strategies and Constitutional {AI} for Clinical Question Answering",
author = "Krishnasamy, Saran and
Wihardjo, Inez",
editor = "Gupta, Deepak and
Thompson, Paul and
Ananiadou, Sophia and
Demner-Fushman, Dina",
booktitle = "Proceedings of the Third Workshop on Patient-Oriented Language Processing ({CL}4{H}ealth) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.cl4health-1.53/",
doi = "10.63317/57f49ajj4svw",
pages = "565--577",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishnasamy-wihardjo-2026-gigitai-archehr">
<titleInfo>
<title>GigitAI at ArchEHR-QA 2026: Prompting Strategies and Constitutional AI for Clinical Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saran</namePart>
<namePart type="family">Krishnasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inez</namePart>
<namePart type="family">Wihardjo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">krishnasamy-wihardjo-2026-gigitai-archehr</identifier>
<identifier type="doi">10.63317/57f49ajj4svw</identifier>
<location>
<url>https://aclanthology.org/2026.cl4health-1.53/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>565</start>
<end>577</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GigitAI at ArchEHR-QA 2026: Prompting Strategies and Constitutional AI for Clinical Question Answering
%A Krishnasamy, Saran
%A Wihardjo, Inez
%Y Gupta, Deepak
%Y Thompson, Paul
%Y Ananiadou, Sophia
%Y Demner-Fushman, Dina
%S Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F krishnasamy-wihardjo-2026-gigitai-archehr
%X 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.
%R 10.63317/57f49ajj4svw
%U https://aclanthology.org/2026.cl4health-1.53/
%U https://doi.org/10.63317/57f49ajj4svw
%P 565-577
Markdown (Informal)
[GigitAI at ArchEHR-QA 2026: Prompting Strategies and Constitutional AI for Clinical Question Answering](https://aclanthology.org/2026.cl4health-1.53/) (Krishnasamy & Wihardjo, CL4Health 2026)
ACL