{"ID":2896264,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.07983","arxiv_id":"2507.07983","title":"Performance and Practical Considerations of Large and Small Language Models in Clinical Decision Support in Rheumatology","abstract":"Large language models (LLMs) show promise for supporting clinical decision-making in complex fields such as rheumatology. Our evaluation shows that smaller language models (SLMs), combined with retrieval-augmented generation (RAG), achieve higher diagnostic and therapeutic performance than larger models, while requiring substantially less energy and enabling cost-efficient, local deployment. These features are attractive for resource-limited healthcare. However, expert oversight remains essential, as no model consistently reached specialist-level accuracy in rheumatology.","short_abstract":"Large language models (LLMs) show promise for supporting clinical decision-making in complex fields such as rheumatology. Our evaluation shows that smaller language models (SLMs), combined with retrieval-augmented generation (RAG), achieve higher diagnostic and therapeutic performance than larger models, while requirin...","url_abs":"https://arxiv.org/abs/2507.07983","url_pdf":"https://arxiv.org/pdf/2507.07983v1","authors":"[\"Sabine Felde\",\"Rüdiger Buchkremer\",\"Gamal Chehab\",\"Christian Thielscher\",\"Jörg HW Distler\",\"Matthias Schneider\",\"Jutta G. Richter\"]","published":"2025-07-10T17:56:03Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}