LIMICS at ArchEHR-QA 2025: Prompting LLMs Beats Fine-Tuned Embeddings

In this paper, we investigated two approaches to clinical question-answering based on patientformulated 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-ofthought reasoning to guide the models in generating answers.The second approach adopts a two-steps structure: first, a textclassification 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.