Position: Vector Prompt Interfaces Should Be Exposed to Enable Customization of Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917314466676736 |
|---|---|
| author | Yang, Liangwei Wang, Shiyu Chen, Haolin Murthy, Rithesh Zhu, Ming Qiu, Jielin Chen, Zixiang Tan, Juntao Zhang, Jianguo Liu, Zhiwei Zhao, Wenting Savarese, Silvio Xiong, Caiming Wang, Huan Heinecke, Shelby |
| author_facet | Yang, Liangwei Wang, Shiyu Chen, Haolin Murthy, Rithesh Zhu, Ming Qiu, Jielin Chen, Zixiang Tan, Juntao Zhang, Jianguo Liu, Zhiwei Zhao, Wenting Savarese, Silvio Xiong, Caiming Wang, Huan Heinecke, Shelby |
| contents | As large language models (LLMs) transition from research prototypes to real-world systems, customization has emerged as a central bottleneck. While text prompts can already customize LLM behavior, we argue that text-only prompting does not constitute a suitable control interface for scalable, stable, and inference-only customization. This position paper argues that model providers should expose \emph{vector prompt inputs} as part of the public interface for customizing LLMs. We support this position with diagnostic evidence showing that vector prompt tuning continues to improve with increasing supervision whereas text-based prompt optimization saturates early, and that vector prompts exhibit dense, global attention patterns indicative of a distinct control mechanism. We further discuss why inference-only customization is increasingly important under realistic deployment constraints, and why exposing vector prompts need not fundamentally increase model leakage risk under a standard black-box threat model. We conclude with a call to action for the community to rethink prompt interfaces as a core component of LLM customization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04292 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Position: Vector Prompt Interfaces Should Be Exposed to Enable Customization of Large Language Models Yang, Liangwei Wang, Shiyu Chen, Haolin Murthy, Rithesh Zhu, Ming Qiu, Jielin Chen, Zixiang Tan, Juntao Zhang, Jianguo Liu, Zhiwei Zhao, Wenting Savarese, Silvio Xiong, Caiming Wang, Huan Heinecke, Shelby Computation and Language As large language models (LLMs) transition from research prototypes to real-world systems, customization has emerged as a central bottleneck. While text prompts can already customize LLM behavior, we argue that text-only prompting does not constitute a suitable control interface for scalable, stable, and inference-only customization. This position paper argues that model providers should expose \emph{vector prompt inputs} as part of the public interface for customizing LLMs. We support this position with diagnostic evidence showing that vector prompt tuning continues to improve with increasing supervision whereas text-based prompt optimization saturates early, and that vector prompts exhibit dense, global attention patterns indicative of a distinct control mechanism. We further discuss why inference-only customization is increasingly important under realistic deployment constraints, and why exposing vector prompts need not fundamentally increase model leakage risk under a standard black-box threat model. We conclude with a call to action for the community to rethink prompt interfaces as a core component of LLM customization. |
| title | Position: Vector Prompt Interfaces Should Be Exposed to Enable Customization of Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2603.04292 |