AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

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

Xueren Ge, Sahil Murtaza, Anthony Cortez, Homa Alemzadeh

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge-augmented question answering

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace CoT with Expert-CoT prompting (add subject area and certification level)OpenBioLLM-70B · EMSQA Public testaccuracy: 59.88 -> 61.92Improved
replace CoT with Expert-CoT promptingQwen3-32B · EMSQA Public testaccuracy: 84.96 -> 85.70Improved
replace CoT with Expert-CoT promptingLlama-3.3-70B · EMSQA Public testaccuracy: 81.89 -> 82.42Improved
use Filter-predicted instead of ground-truth expertise in Expert-CoT (ablation)Qwen3-32B · EMSQA Public testaccuracy: 85.70 -> 85.57No clear effect
add subject-area filtered retrieval (ExpertRAG FTR/RTF) instead of global retrieval (ablation)Qwen3-4B RAG with CoT · EMSQA Public testaccuracy: 78.12 -> 81.11Improved
add Expert-CoT to global RAG (ablation)Qwen3-4B global RAG · EMSQA Public testaccuracy: 78.12 -> 79.59Improved
combine ExpertRAG (RTF) with Expert-CoT using ground-truth expertise (ablation)Qwen3-4B · EMSQA Public testaccuracy: 78.12 -> 82.24Improved
use Filter-predicted instead of ground-truth expertise in ExpertRAG (ablation)Qwen3-4B ExpertRAG RTF + Expert-CoT · EMSQA Public testaccuracy: 82.24 -> 80.95Hurt
add KB retrieval instead of patient-record retrieval (ablation)Qwen3-4B RAG · EMSQA Public testaccuracy: 73.02 -> 76.49Improved
combine KB and patient records in global retrieval (ablation)Qwen3-4B RAG · EMSQA Public testaccuracy: 76.49 -> 78.12Improved
increase few-shot examples from 4 to 32Qwen3-32B · EMSQA Public testaccuracy: 84.41 -> 81.13Hurt
train Filter with LoRA and two classification heads instead of prompting an LLM for expertiseQwen3-4B · EMSQA Public subject-area classificationmicro F1: 59.72 -> 80.72Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy