mlsanityData to 14 Oct 2026

LLM-based Prompt Ensemble for Reliable Medical Entity Recognition from EHRs

arXiv 2505.08704 ↗First posted 13 May 2025cs.AI cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Electronic Health Records (EHRs) are digital records of patient information, often containing unstructured clinical text. Named Entity Recognition (NER) is essential in EHRs for extracting key medical entities like problems, tests, and treatments to support downstream clinical applications. This paper explores prompt-based medical entity recognition using large language models (LLMs), specifically GPT-4o and DeepSeek-R1, guided by various prompt engineering techniques, including zero-shot, few-shot, and an ensemble approach. Among all strategies, GPT-4o with prompt ensemble achieved the highest classification performance with an F1-score of 0.95 and recall of 0.98, outperforming DeepSeek-R1 on the task. The ensemble method improved reliability by aggregating outputs through embedding-based similarity and majority voting.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 9 of its 20 references that are in the map. First posted on arXiv 13 May 2025.

Builds on

9 of 20 references.

References · 9

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2024GPT-4o System Cardcited by 4,588
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2019Publicly Available Clinical BERT Embeddingscited by 1,002
  6. 2023GPT-NER: Named Entity Recognition via Large Language Modelscited by 160
  7. 2024LLM on FHIR -- Demystifying Health Recordscited by 9
  8. 2024How Reliable AI Chatbots are for Disease Prediction from Patient Complaints?cited by 5
  9. 2024Autocompletion of Chief Complaints in the Electronic Health Records using Large Language Modelscited by 4

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025FiNERweb: Datasets and Artifacts for Scalable Multilingual Named Entity Recognitioncited by 3
  2. 2025Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Modelscited by 0
  3. 2025multiMentalRoBERTa: A Fine-tuned Multiclass Classifier for Mental Health Disordercited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024LLMs in Biomedicine: A study on clinical Named Entity Recognition
  2. 2024Large Language Models Struggle in Token-Level Clinical Named Entity Recognition
  3. 2025Retrieval augmented generation based dynamic prompting for few-shot biomedical named entity recognition using large language models
  4. 2024LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction
  5. 2023An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing
  6. 2023How far is Language Model from 100% Few-shot Named Entity Recognition in Medical Domain
  7. 2025An evaluation of DeepSeek Models in Biomedical Natural Language Processing
  8. 2024LLM-IE: A Python Package for Generative Information Extraction with Large Language Models