Dokument: Evaluating base and retrieval augmented LLMs with document or online support for evidence based neurology
| Titel: | Evaluating base and retrieval augmented LLMs with document or online support for evidence based neurology | |||||||
| URL für Lesezeichen: | https://docserv.uni-duesseldorf.de/servlets/DocumentServlet?id=69394 | |||||||
| URN (NBN): | urn:nbn:de:hbz:061-20250417-105425-3 | |||||||
| Kollektion: | Publikationen | |||||||
| Sprache: | Englisch | |||||||
| Dokumententyp: | Wissenschaftliche Texte » Artikel, Aufsatz | |||||||
| Medientyp: | Text | |||||||
| Autoren: | Masanneck, Lars [Autor] Meuth, Sven G. [Autor] Pawlitzki, Marc [Autor] | |||||||
| Dateien: |
| |||||||
| Beschreibung: | Effectively managing evidence-based information is increasingly challenging. This study tested large language models (LLMs), including document- and online-enabled retrieval-augmented generation (RAG) systems, using 13 recent neurology guidelines across 130 questions. Results showed substantial variability. RAG improved accuracy compared to base models but still produced potentially harmful answers. RAG-based systems performed worse on case-based than knowledge-based questions. Further refinement and improved regulation is needed for safe clinical integration of RAG-enhanced LLMs. | |||||||
| Rechtliche Vermerke: | Originalveröffentlichung:
Masanneck, L., Meuth, S., & Pawlitzki, M. (2025). Evaluating base and retrieval augmented LLMs with document or online support for evidence based neurology. Npj Digital Medicine, 8, Article 137. https://doi.org/10.1038/s41746-025-01536-y | |||||||
| Lizenz: |  Dieses Werk ist lizenziert unter einer Creative Commons Namensnennung 4.0 International Lizenz | |||||||
| Fachbereich / Einrichtung: | Medizinische Fakultät | |||||||
| Dokument erstellt am: | 17.04.2025 | |||||||
| Dateien geändert am: | 17.04.2025 |
