@inproceedings{anghel-etal-2026-patient2paper,
    title = "{P}atient2{P}aper at {\#}{SMM}4{H}-{H}ea{RD} 2026: Retrieval-Augmented Few-Shot Generation for Clinical Note Synthesis",
    author = "Anghel, Ioan-Tudor-Alexandru  and
      Andrei, Timotei  and
      Bogdan, Com{\^a}rdici Marian  and
      S{\^a}icu, Carina",
    editor = "Lopez-Garcia, Guillermo  and
      Gonzalez-Hernandez, Graciela",
    booktitle = "Proceedings of the 11th Social Media Mining for Health Research and Applications ({SMM}4{H}-{H}ea{RD} 2026) Workshop and Shared Tasks",
    month = jul,
    year = "2026",
    address = "San Diego, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.smm4h-1.11/",
    pages = "61--66",
    ISBN = "979-8-89176-432-3",
    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."
}