Retrieval-Augmented Generation in Biomedicine: A Survey of Technologies, Datasets, and Clinical Applications
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909968013197312 |
|---|---|
| author | He, Jiawei Zhang, Boya Rouhizadeh, Hossein Chen, Yingjian Yang, Rui Lu, Jin Chen, Xudong Liu, Nan Teodoro, Douglas |
| author_facet | He, Jiawei Zhang, Boya Rouhizadeh, Hossein Chen, Yingjian Yang, Rui Lu, Jin Chen, Xudong Liu, Nan Teodoro, Douglas |
| contents | Large language models (LLMs) in biomedicine face a fundamental conflict between static parameter knowledge and the dynamic nature of clinical evidence. Retrieval-Augmented Generation (RAG) addresses this by grounding generation in external data, yet it introduces new complexities in latency and architecture. This survey synthesizes the biomedical RAG landscape (2020-2025), classifying systems into naive, advanced, and modular paradigms. Beyond a technological taxonomy, we formalize the biomedical RAG trilemma, identifying the inherent trade-offs between reasoning depth, inference latency, and data privacy that constrain current clinical deployment. We analyze how recent agentic workflows enhance diagnostic reasoning but risk prohibitive latency, and how privacy constraints dictate the choice between powerful cloud-based models and local deployment. Finally, we outline the alignment gap in multimodal RAG and propose future directions for self-correcting, verifiable clinical agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01146 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Retrieval-Augmented Generation in Biomedicine: A Survey of Technologies, Datasets, and Clinical Applications He, Jiawei Zhang, Boya Rouhizadeh, Hossein Chen, Yingjian Yang, Rui Lu, Jin Chen, Xudong Liu, Nan Teodoro, Douglas Other Quantitative Biology Large language models (LLMs) in biomedicine face a fundamental conflict between static parameter knowledge and the dynamic nature of clinical evidence. Retrieval-Augmented Generation (RAG) addresses this by grounding generation in external data, yet it introduces new complexities in latency and architecture. This survey synthesizes the biomedical RAG landscape (2020-2025), classifying systems into naive, advanced, and modular paradigms. Beyond a technological taxonomy, we formalize the biomedical RAG trilemma, identifying the inherent trade-offs between reasoning depth, inference latency, and data privacy that constrain current clinical deployment. We analyze how recent agentic workflows enhance diagnostic reasoning but risk prohibitive latency, and how privacy constraints dictate the choice between powerful cloud-based models and local deployment. Finally, we outline the alignment gap in multimodal RAG and propose future directions for self-correcting, verifiable clinical agents. |
| title | Retrieval-Augmented Generation in Biomedicine: A Survey of Technologies, Datasets, and Clinical Applications |
| topic | Other Quantitative Biology |
| url | https://arxiv.org/abs/2505.01146 |