Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2506.00051 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911196509110272 |
|---|---|
| author | Quirke, Philip Oozeer, Narmeen Bandi, Chaithanya Abdullah, Amir Hoelscher-Obermaier, Jason Phillips, Jeff M. Greaves, Joshua Neo, Clement Lan, Michael Barez, Fazl Upadhyay, Shriyash |
| author_facet | Quirke, Philip Oozeer, Narmeen Bandi, Chaithanya Abdullah, Amir Hoelscher-Obermaier, Jason Phillips, Jeff M. Greaves, Joshua Neo, Clement Lan, Michael Barez, Fazl Upadhyay, Shriyash |
| contents | This position paper argues that the prevailing trajectory toward ever larger, more expensive generalist foundation models controlled by a handful of companies limits innovation and constrains progress. We challenge this approach by advocating for an "Expert Orchestration" (EO) framework as a superior alternative that democratizes LLM advancement. Our proposed framework intelligently selects from many existing models based on query requirements and decomposition, focusing on identifying what models do well rather than how they work internally. Independent "judge" models assess various models' capabilities across dimensions that matter to users, while "router" systems direct queries to the most appropriate specialists within an approved set. This approach delivers superior performance by leveraging targeted expertise rather than forcing costly generalist models to address all user requirements. EO enhances transparency, control, alignment, performance, safety and democratic participation through intelligent model selection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00051 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Language Models Quirke, Philip Oozeer, Narmeen Bandi, Chaithanya Abdullah, Amir Hoelscher-Obermaier, Jason Phillips, Jeff M. Greaves, Joshua Neo, Clement Lan, Michael Barez, Fazl Upadhyay, Shriyash Computers and Society This position paper argues that the prevailing trajectory toward ever larger, more expensive generalist foundation models controlled by a handful of companies limits innovation and constrains progress. We challenge this approach by advocating for an "Expert Orchestration" (EO) framework as a superior alternative that democratizes LLM advancement. Our proposed framework intelligently selects from many existing models based on query requirements and decomposition, focusing on identifying what models do well rather than how they work internally. Independent "judge" models assess various models' capabilities across dimensions that matter to users, while "router" systems direct queries to the most appropriate specialists within an approved set. This approach delivers superior performance by leveraging targeted expertise rather than forcing costly generalist models to address all user requirements. EO enhances transparency, control, alignment, performance, safety and democratic participation through intelligent model selection. |
| title | Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Language Models |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2506.00051 |