Leveraging Language Models and RAG for Efficient Knowledge Discovery in Clinical Environments
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914239165235200 |
|---|---|
| author | Ko, Seokhwan Lee, Donghyeon Chun, Jaewoo Han, Hyungsoo Cho, Junghwan |
| author_facet | Ko, Seokhwan Lee, Donghyeon Chun, Jaewoo Han, Hyungsoo Cho, Junghwan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04209 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Language Models and RAG for Efficient Knowledge Discovery in Clinical Environments Ko, Seokhwan Lee, Donghyeon Chun, Jaewoo Han, Hyungsoo Cho, Junghwan Computation and Language 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. |
| title | Leveraging Language Models and RAG for Efficient Knowledge Discovery in Clinical Environments |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.04209 |