EUVIMEDEUVIMED entdecken
Crossref

Expert-Guided Prompting and Retrieval-Augmented Generation for Emergency Medical Service Question Answering

Xueren Ge, Sahil Murtaza, Anthony Cortez, Homa Alemzadeh

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (36) · 30798-30806

DOI: 10.1609/aaai.v40i36.40337 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xueren Ge und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) have shown promise in medical question answering, yet they often overlook the domain-specific expertise that professionals depend on-such as the clinical subject areas (e.g., trauma, airway) and the certification level (e.g., EMT, Paramedic). Existing approaches typically apply general-purpose prompting or retrieval strategies without leveraging this structured context, limiting performance in high-stakes settings. We address this gap with EMSQA, an 24.3K-question multiple-choice dataset spanning 10 clinical subject areas and 4 certification levels, accompanied by curated, subject area-aligned knowledge bases (40K documents and 2M tokens). Building on EMSQA, we introduce (i) Expert-CoT, a prompting strategy that conditions chain-of-thought (CoT) reasoning on specific clinical subject area and certification level, and (ii) ExpertRAG, a retrieval-augmented generation pipeline that grounds responses in subject area-aligned documents and real-world patient data. Experiments on 4 LLMs show that Expert-CoT improves up to 2.05% over vanilla CoT prompting. Additionally, combining Expert-CoT with ExpertRAG yields up to a 4.59% accuracy gain over standard RAG baselines. Notably, the 32B expertise-augmented LLMs pass all the computer-adaptive EMS certification simulation exams.

Zitieren

APA

Ge, X., Murtaza, S., Cortez, A., & Alemzadeh, H. (2026). Expert-Guided Prompting and Retrieval-Augmented Generation for Emergency Medical Service Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence, 40(36), 30798-30806. https://doi.org/10.1609/aaai.v40i36.40337

Vancouver

Ge X, Murtaza S, Cortez A, Alemzadeh H. Expert-Guided Prompting and Retrieval-Augmented Generation for Emergency Medical Service Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(36):30798-30806. doi:10.1609/aaai.v40i36.40337

BibTeX
@article{Ge2026,
  author = {Ge, Xueren and Murtaza, Sahil and Cortez, Anthony and Alemzadeh, Homa},
  title = {Expert-Guided Prompting and Retrieval-Augmented Generation for Emergency Medical Service Question Answering},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {36},
  pages = {30798--30806},
  doi = {10.1609/aaai.v40i36.40337}
}
Kostenlos starten →