Dynamic Fog Computing for Enhanced LLM Execution in Medical Applications
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929628531130368 |
|---|---|
| author | Zagar, Philipp Ravi, Vishnu Aalami, Lauren Krusche, Stephan Aalami, Oliver Schmiedmayer, Paul |
| author_facet | Zagar, Philipp Ravi, Vishnu Aalami, Lauren Krusche, Stephan Aalami, Oliver Schmiedmayer, Paul |
| contents | The ability of large language models (LLMs) to transform, interpret, and comprehend vast quantities of heterogeneous data presents a significant opportunity to enhance data-driven care delivery. However, the sensitive nature of protected health information (PHI) raises valid concerns about data privacy and trust in remote LLM platforms. In addition, the cost associated with cloud-based artificial intelligence (AI) services continues to impede widespread adoption. To address these challenges, we propose a shift in the LLM execution environment from opaque, centralized cloud providers to a decentralized and dynamic fog computing architecture. By executing open-weight LLMs in more trusted environments, such as the user's edge device or a fog layer within a local network, we aim to mitigate the privacy, trust, and financial challenges associated with cloud-based LLMs. We further present SpeziLLM, an open-source framework designed to facilitate rapid and seamless leveraging of different LLM execution layers and lowering barriers to LLM integration in digital health applications. We demonstrate SpeziLLM's broad applicability across six digital health applications, showcasing its versatility in various healthcare settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04680 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dynamic Fog Computing for Enhanced LLM Execution in Medical Applications Zagar, Philipp Ravi, Vishnu Aalami, Lauren Krusche, Stephan Aalami, Oliver Schmiedmayer, Paul Computation and Language Artificial Intelligence Cryptography and Security The ability of large language models (LLMs) to transform, interpret, and comprehend vast quantities of heterogeneous data presents a significant opportunity to enhance data-driven care delivery. However, the sensitive nature of protected health information (PHI) raises valid concerns about data privacy and trust in remote LLM platforms. In addition, the cost associated with cloud-based artificial intelligence (AI) services continues to impede widespread adoption. To address these challenges, we propose a shift in the LLM execution environment from opaque, centralized cloud providers to a decentralized and dynamic fog computing architecture. By executing open-weight LLMs in more trusted environments, such as the user's edge device or a fog layer within a local network, we aim to mitigate the privacy, trust, and financial challenges associated with cloud-based LLMs. We further present SpeziLLM, an open-source framework designed to facilitate rapid and seamless leveraging of different LLM execution layers and lowering barriers to LLM integration in digital health applications. We demonstrate SpeziLLM's broad applicability across six digital health applications, showcasing its versatility in various healthcare settings. |
| title | Dynamic Fog Computing for Enhanced LLM Execution in Medical Applications |
| topic | Computation and Language Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2408.04680 |