PRewrite: Prompt Rewriting with Reinforcement Learning
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_ | 1866916280785698816 |
|---|---|
| author | Kong, Weize Hombaiah, Spurthi Amba Zhang, Mingyang Mei, Qiaozhu Bendersky, Michael |
| author_facet | Kong, Weize Hombaiah, Spurthi Amba Zhang, Mingyang Mei, Qiaozhu Bendersky, Michael |
| contents | Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a "trial and error" fashion that can be time consuming, ineffective, and sub-optimal. Even for the prompts which seemingly work well, there is always a lingering question: can the prompts be made better with further modifications?
To address these problems, we investigate automated prompt engineering in this paper. Specifically, we propose PRewrite, an automated method to rewrite an under-optimized prompt to a more effective prompt. We instantiate the prompt rewriter using a LLM. The rewriter LLM is trained using reinforcement learning to optimize the performance on a given downstream task. We conduct experiments on diverse benchmark datasets, which demonstrates the effectiveness of PRewrite. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08189 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PRewrite: Prompt Rewriting with Reinforcement Learning Kong, Weize Hombaiah, Spurthi Amba Zhang, Mingyang Mei, Qiaozhu Bendersky, Michael Artificial Intelligence Computation and Language Machine Learning Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a "trial and error" fashion that can be time consuming, ineffective, and sub-optimal. Even for the prompts which seemingly work well, there is always a lingering question: can the prompts be made better with further modifications? To address these problems, we investigate automated prompt engineering in this paper. Specifically, we propose PRewrite, an automated method to rewrite an under-optimized prompt to a more effective prompt. We instantiate the prompt rewriter using a LLM. The rewriter LLM is trained using reinforcement learning to optimize the performance on a given downstream task. We conduct experiments on diverse benchmark datasets, which demonstrates the effectiveness of PRewrite. |
| title | PRewrite: Prompt Rewriting with Reinforcement Learning |
| topic | Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2401.08189 |