Leveraging Language Models and RAG for Efficient Knowledge Discovery in Clinical Environments

• URL: http://arxiv.org/abs/2601.04209v1
• Date: Wed, 10 Dec 2025 05:01:56 GMT
• Title: Leveraging Language Models and RAG for Efficient Knowledge Discovery in Clinical Environments
• Authors: Seokhwan Ko, Donghyeon Lee, Jaewoo Chun, Hyungsoo Han, Junghwan Cho,
• Abstract summary: Large language models (LLMs) are increasingly recognized as valuable tools across the medical environment.<n>However, strict privacy and network security regulations in hospital settings require that sensitive data be processed within fully local infrastructures.<n>We developed and evaluated a retrieval-augmented generation (RAG) system designed to recommend research collaborators based on PubMed publications authored by members of a medical institution.
• Score: 4.352281022671451
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly recognized as valuable tools across the medical environment, supporting clinical, research, and administrative workflows. However, strict privacy and network security regulations in hospital settings require that sensitive data be processed within fully local infrastructures. Within this context, we developed and evaluated a retrieval-augmented generation (RAG) system designed to recommend research collaborators based on PubMed publications authored by members of a medical institution. The system utilizes PubMedBERT for domain-specific embedding generation and a locally deployed LLaMA3 model for generative synthesis. This study demonstrates the feasibility and utility of integrating domain-specialized encoders with lightweight LLMs to support biomedical knowledge discovery under local deployment constraints.

Related papers

• A Federated and Parameter-Efficient Framework for Large Language Model Training in Medicine [59.78991974851707]
  Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis.<n>Most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems.<n>We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications.
  arXiv  Detail & Related papers  (2026-01-29T18:48:21Z)
• Utilizing Large Language Models for Zero-Shot Medical Ontology Extension from Clinical Notes [13.564947974902429]
  We propose CLOZE, a novel framework that uses large language models (LLMs) to automatically extract medical entities from clinical notes.<n>By capitalizing on the strong language understanding and extensive knowledge of pre-trained LLMs, CLOZE effectively identifies disease-related concepts and captures complex hierarchical relationships.
  arXiv  Detail & Related papers  (2025-11-20T17:00:46Z)
• Biomedical Literature Q&A System Using Retrieval-Augmented Generation (RAG) [0.0]
  This work presents a Biomedical Literature Question Answering (Q&A) system based on a Retrieval-Augmented Generation architecture.<n>The system integrates diverse sources, including PubMed articles, curated Q&A datasets, and medical encyclopedias.<n>The system supports both general medical queries and domain-specific tasks, with a focused evaluation on breast cancer literature.
  arXiv  Detail & Related papers  (2025-09-05T21:29:52Z)
• LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation [58.25892575437433]
  evaluating large language models (LLMs) in medicine is crucial because medical applications require high accuracy with little room for error.<n>We present LLMEval-Med, a new benchmark covering five core medical areas, including 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios.
  arXiv  Detail & Related papers  (2025-06-04T15:43:14Z)
• Advancing AI Research Assistants with Expert-Involved Learning [84.30323604785646]
  Large language models (LLMs) and large multimodal models (LMMs) promise to accelerate biomedical discovery, yet their reliability remains unclear.<n>We introduce ARIEL (AI Research Assistant for Expert-in-the-Loop Learning), an open-source evaluation and optimization framework.<n>We find that state-of-the-art models generate fluent but incomplete summaries, whereas LMMs struggle with detailed visual reasoning.
  arXiv  Detail & Related papers  (2025-05-03T14:21:48Z)
• Reviewing Clinical Knowledge in Medical Large Language Models: Training and Beyond [17.18909853414425]
  Clinical knowledge has been extensively examined within real-world medical practices.<n>There has been a notable increase in research efforts aimed at integrating this type of knowledge into large language models.<n>We review the various initiatives to embed clinical knowledge into training-based, KG-supported, and RAG-assisted LLMs.
  arXiv  Detail & Related papers  (2025-02-28T12:00:51Z)
• Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering [70.44269982045415]
  Retrieval-augmented generation (RAG) has emerged as a promising approach to enhance the performance of large language models (LLMs) We introduce Medical Retrieval-Augmented Generation Benchmark (MedRGB) that provides various supplementary elements to four medical QA datasets. Our experimental results reveals current models' limited ability to handle noise and misinformation in the retrieved documents.
  arXiv  Detail & Related papers  (2024-11-14T06:19:18Z)
• STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and Beyond [68.47402386668846]
  We introduce Structured Reasoning In Critical Text Assessment (STRICTA) to model text assessment as an explicit, step-wise reasoning process.<n>STRICTA breaks down the assessment into a graph of interconnected reasoning steps drawing on causality theory.<n>We apply STRICTA to a dataset of over 4000 reasoning steps from roughly 40 biomedical experts on more than 20 papers.
  arXiv  Detail & Related papers  (2024-09-09T06:55:37Z)
• LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction [13.965777046473885]
  Large Language Models (LLMs) are increasingly adopted for applications in healthcare.<n>They reach the performance of domain experts on tasks such as question answering and document summarisation.<n>It is unclear how well LLMs perform on tasks that are traditionally pursued in the biomedical domain.
  arXiv  Detail & Related papers  (2024-08-22T09:37:40Z)
• MedKP: Medical Dialogue with Knowledge Enhancement and Clinical Pathway Encoding [48.348511646407026]
  We introduce the Medical dialogue with Knowledge enhancement and clinical Pathway encoding framework. The framework integrates an external knowledge enhancement module through a medical knowledge graph and an internal clinical pathway encoding via medical entities and physician actions.
  arXiv  Detail & Related papers  (2024-03-11T10:57:45Z)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
  We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
  arXiv  Detail & Related papers  (2024-02-15T06:46:48Z)
• Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Review [16.008511195589925]
  Large language models (LLMs) have shown promising capabilities in mimicking human-level language comprehension and reasoning. This paper provides a comprehensive review on the applications and implications of LLMs in medicine.
  arXiv  Detail & Related papers  (2023-11-03T13:51:36Z)
• UmlsBERT: Clinical Domain Knowledge Augmentation of Contextual Embeddings Using the Unified Medical Language System Metathesaurus [73.86656026386038]
  We introduce UmlsBERT, a contextual embedding model that integrates domain knowledge during the pre-training process. By applying these two strategies, UmlsBERT can encode clinical domain knowledge into word embeddings and outperform existing domain-specific models.
  arXiv  Detail & Related papers  (2020-10-20T15:56:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.