NurseLLM: The First Specialized Language Model for Nursing

2025-10-08

AI Summary

Despite significant advances in large language models (LLMs) for healthcare, their application in highly specialized domains such as nursing remains unexplored. This work addresses this gap by introducing NurseLLM, the first domain-specific LLM tailored for nursing. Methodologically, we (1) construct the first large-scale, human-verified nursing multiple-choice question dataset; (2) design a multi-stage data generation pipeline and instruction-tuning paradigm; and (3) incorporate reasoning enhancement mechanisms alongside a multi-agent collaborative reasoning framework. Experimental results demonstrate that NurseLLM significantly outperforms comparably sized general-purpose and medical-domain LLMs across multiple nursing benchmarks. These findings underscore the critical importance of fine-grained domain specialization for advancing nursing AI. Our contributions include: (i) a foundational nursing-specific LLM; (ii) high-quality, expert-annotated training data; and (iii) a reproducible, standardized evaluation infrastructure—collectively establishing a new benchmark for intelligent nursing systems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Application Domains: Humanities & Computational Social Science

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Recent advancements in large language models (LLMs) have significantly transformed medical systems. However, their potential within specialized domains such as nursing remains largely underexplored. In this work, we introduce NurseLLM, the first nursing-specialized LLM tailored for multiple choice question-answering (MCQ) tasks. We develop a multi-stage data generation pipeline to build the first large scale nursing MCQ dataset to train LLMs on a broad spectrum of nursing topics. We further introduce multiple nursing benchmarks to enable rigorous evaluation. Our extensive experiments demonstrate that NurseLLM outperforms SoTA general-purpose and medical-specialized LLMs of comparable size on different benchmarks, underscoring the importance of a specialized LLM for the nursing domain. Finally, we explore the role of reasoning and multi-agent collaboration systems in nursing, highlighting their promise for future research and applications.

Problem

• Developing the first specialized language model for nursing
• Creating a large-scale nursing MCQ dataset for training
• Establishing benchmarks to evaluate nursing-specific LLM performance

Innovation

• First specialized LLM for nursing domain
• Multi-stage pipeline generates nursing MCQ dataset
• Outperforms comparable medical-specialized LLMs