<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="anghel-etal-2026-patient2paper">
    <titleInfo>
        <title>Patient2Paper at #SMM4H-HeaRD 2026: Retrieval-Augmented Few-Shot Generation for Clinical Note Synthesis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ioan-Tudor-Alexandru</namePart>
        <namePart type="family">Anghel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Timotei</namePart>
        <namePart type="family">Andrei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Comârdici</namePart>
        <namePart type="given">Marian</namePart>
        <namePart type="family">Bogdan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carina</namePart>
        <namePart type="family">Sâicu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Guillermo</namePart>
            <namePart type="family">Lopez-Garcia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Graciela</namePart>
            <namePart type="family">Gonzalez-Hernandez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-432-3</identifier>
    </relatedItem>
    <abstract>We present a retrieval-augmented few-shot system for the MedSynth Dial2Note shared task at SMM4H-HEARD 2026, placing 3rd on the official leaderboard (0.51 avg). Across 28 configurations, we find that retrieval design (hybrid BM25 + medical-domain dense fused via RRF) and prompt presentation format (few-shot examples as conversation turns) are the primary quality drivers, while model scale has surprisingly limited impact: Llama 3.2:3B, Llama 3.1:8B and GPT-4o mini remain within a narrow band on our locally computed scores. Our final submission used GPT-4o mini with k=3 few-shot examples retrieved by RRF over BioLORD-2023 embeddings. We report a full ablation, including negative results, to show where the gains come from and where further engineering stops paying off.</abstract>
    <identifier type="citekey">anghel-etal-2026-patient2paper</identifier>
    <location>
        <url>https://aclanthology.org/2026.smm4h-1.11/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>61</start>
            <end>66</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Patient2Paper at #SMM4H-HeaRD 2026: Retrieval-Augmented Few-Shot Generation for Clinical Note Synthesis
%A Anghel, Ioan-Tudor-Alexandru
%A Andrei, Timotei
%A Bogdan, Comârdici Marian
%A Sâicu, Carina
%Y Lopez-Garcia, Guillermo
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, United States
%@ 979-8-89176-432-3
%F anghel-etal-2026-patient2paper
%X We present a retrieval-augmented few-shot system for the MedSynth Dial2Note shared task at SMM4H-HEARD 2026, placing 3rd on the official leaderboard (0.51 avg). Across 28 configurations, we find that retrieval design (hybrid BM25 + medical-domain dense fused via RRF) and prompt presentation format (few-shot examples as conversation turns) are the primary quality drivers, while model scale has surprisingly limited impact: Llama 3.2:3B, Llama 3.1:8B and GPT-4o mini remain within a narrow band on our locally computed scores. Our final submission used GPT-4o mini with k=3 few-shot examples retrieved by RRF over BioLORD-2023 embeddings. We report a full ablation, including negative results, to show where the gains come from and where further engineering stops paying off.
%U https://aclanthology.org/2026.smm4h-1.11/
%P 61-66

Markdown (Informal)

[Patient2Paper at #SMM4H-HeaRD 2026: Retrieval-Augmented Few-Shot Generation for Clinical Note Synthesis](https://aclanthology.org/2026.smm4h-1.11/) (Anghel et al., SMM4H 2026)

• Patient2Paper at #SMM4H-HeaRD 2026: Retrieval-Augmented Few-Shot Generation for Clinical Note Synthesis (Anghel et al., SMM4H 2026)

ACL

• Ioan-Tudor-Alexandru Anghel, Timotei Andrei, Comârdici Marian Bogdan, and Carina Sâicu. 2026. Patient2Paper at #SMM4H-HeaRD 2026: Retrieval-Augmented Few-Shot Generation for Clinical Note Synthesis. In Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks, pages 61–66, San Diego, United States. Association for Computational Linguistics.