Black-box Prompt Tuning with Subspace Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911919373287424 |
|---|---|
| author | Zheng, Yuanhang Tan, Zhixing Li, Peng Liu, Yang |
| author_facet | Zheng, Yuanhang Tan, Zhixing Li, Peng Liu, Yang |
| contents | Black-box prompt tuning employs derivative-free optimization algorithms to learn prompts within low-dimensional subspaces rather than back-propagating through the network of Large Language Models (LLMs). Recent studies reveal that black-box prompt tuning lacks versatility across tasks and LLMs, which we believe is related to the suboptimal choice of subspaces. In this paper, we introduce Black-box prompt tuning with Subspace Learning (BSL) to enhance the versatility of black-box prompt tuning. Based on the assumption that nearly optimal prompts for similar tasks reside in a common subspace, we propose identifying such subspaces through meta-learning on a collection of similar source tasks. Consequently, for a target task that shares similarities with the source tasks, we expect that optimizing within the identified subspace can yield a prompt that performs well on the target task. Experimental results confirm that our BSL framework consistently achieves competitive performance across various downstream tasks and LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_03518 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Black-box Prompt Tuning with Subspace Learning Zheng, Yuanhang Tan, Zhixing Li, Peng Liu, Yang Computation and Language Artificial Intelligence Black-box prompt tuning employs derivative-free optimization algorithms to learn prompts within low-dimensional subspaces rather than back-propagating through the network of Large Language Models (LLMs). Recent studies reveal that black-box prompt tuning lacks versatility across tasks and LLMs, which we believe is related to the suboptimal choice of subspaces. In this paper, we introduce Black-box prompt tuning with Subspace Learning (BSL) to enhance the versatility of black-box prompt tuning. Based on the assumption that nearly optimal prompts for similar tasks reside in a common subspace, we propose identifying such subspaces through meta-learning on a collection of similar source tasks. Consequently, for a target task that shares similarities with the source tasks, we expect that optimizing within the identified subspace can yield a prompt that performs well on the target task. Experimental results confirm that our BSL framework consistently achieves competitive performance across various downstream tasks and LLMs. |
| title | Black-box Prompt Tuning with Subspace Learning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2305.03518 |