@inproceedings{remaki-etal-2025-limics,
    title = "{LIMICS} at {A}rch{EHR}-{QA} 2025: Prompting {LLM}s Beats Fine-Tuned Embeddings",
    author = "Remaki, Adam  and
      Violle, Armand  and
      Natraj, Vikram  and
      Gu{\'e}vel, {\'E}tienne  and
      Redjdal, Akram",
    editor = "Soni, Sarvesh  and
      Demner-Fushman, Dina",
    booktitle = "BioNLP 2025 Shared Tasks",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.bionlp-share.18/",
    pages = "150--159",
    ISBN = "979-8-89176-276-3",
    abstract = "In this paper, we investigated two approaches to clinical question-answering based on patient-formulated questions, supported by their narratives and brief medical records. The first approach leverages zero- and few-shot prompt engineering techniques with GPT-based Large Language Models (LLMs), incorporating strategies such as prompt chaining and chain-of-thought reasoning to guide the models in generating answers. The second approach adopts a two-steps structure: first, a text-classification stage uses embedding-based models (e.g., BERT variants) to identify sentences within the medical record that are most relevant to the given question; then, we prompt an LLM to paraphrase them into an answer so that it is generated exclusively from these selected sentences. Our empirical results demonstrate that the first approach outperforms the classification-guided pipeline, achieving the highest score on the development set and the test set using prompt chaining. Code: github.com/armandviolle/BioNLP-2025"
}