A Survey on Prompt Tuning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912472769757184 |
|---|---|
| author | Li, Zongqian Su, Yixuan Collier, Nigel |
| author_facet | Li, Zongqian Su, Yixuan Collier, Nigel |
| contents | This survey reviews prompt tuning, a parameter-efficient approach for adapting language models by prepending trainable continuous vectors while keeping the model frozen. We classify existing approaches into two categories: direct prompt learning and transfer learning. Direct prompt learning methods include: general optimization approaches, encoder-based methods, decomposition strategies, and mixture-of-experts frameworks. Transfer learning methods consist of: general transfer approaches, encoder-based methods, and decomposition strategies. For each method, we analyze method designs, innovations, insights, advantages, and disadvantages, with illustrative visualizations comparing different frameworks. We identify challenges in computational efficiency and training stability, and discuss future directions in improving training robustness and broadening application scope. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06085 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey on Prompt Tuning Li, Zongqian Su, Yixuan Collier, Nigel Computation and Language This survey reviews prompt tuning, a parameter-efficient approach for adapting language models by prepending trainable continuous vectors while keeping the model frozen. We classify existing approaches into two categories: direct prompt learning and transfer learning. Direct prompt learning methods include: general optimization approaches, encoder-based methods, decomposition strategies, and mixture-of-experts frameworks. Transfer learning methods consist of: general transfer approaches, encoder-based methods, and decomposition strategies. For each method, we analyze method designs, innovations, insights, advantages, and disadvantages, with illustrative visualizations comparing different frameworks. We identify challenges in computational efficiency and training stability, and discuss future directions in improving training robustness and broadening application scope. |
| title | A Survey on Prompt Tuning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.06085 |