Ultra-Low-Dimensional Prompt Tuning via Random Projection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910121421963264 |
|---|---|
| author | Wu, Zijun Hao, Yongchang Mou, Lili |
| author_facet | Wu, Zijun Hao, Yongchang Mou, Lili |
| contents | Large language models achieve state-of-the-art performance but are increasingly costly to fine-tune. Prompt tuning is a parameter-efficient fine-tuning method that addresses parameter-efficiency by learning prompt embeddings, but these embeddings are typically tied to the model's hidden dimensionality, limiting parameter saving. In this paper, we propose Ultra-Low-dimensional Prompt Tuning (ULPT), a simple yet effective method that optimizes prompts in a low-dimensional space (e.g., 2D) and uses a frozen random matrix for up-projection. ULPT can achieve 98% reduction in the training parameters compared to vanilla prompt tuning while preserving performance. Our extensive experiments across over 20 NLP tasks demonstrate that ULPT consistently outperforms recent parameter-efficient tuning methods using significantly fewer parameters, making it well-suited as a storage-efficient framework for massive LLM customization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_04501 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ultra-Low-Dimensional Prompt Tuning via Random Projection Wu, Zijun Hao, Yongchang Mou, Lili Computation and Language Large language models achieve state-of-the-art performance but are increasingly costly to fine-tune. Prompt tuning is a parameter-efficient fine-tuning method that addresses parameter-efficiency by learning prompt embeddings, but these embeddings are typically tied to the model's hidden dimensionality, limiting parameter saving. In this paper, we propose Ultra-Low-dimensional Prompt Tuning (ULPT), a simple yet effective method that optimizes prompts in a low-dimensional space (e.g., 2D) and uses a frozen random matrix for up-projection. ULPT can achieve 98% reduction in the training parameters compared to vanilla prompt tuning while preserving performance. Our extensive experiments across over 20 NLP tasks demonstrate that ULPT consistently outperforms recent parameter-efficient tuning methods using significantly fewer parameters, making it well-suited as a storage-efficient framework for massive LLM customization. |
| title | Ultra-Low-Dimensional Prompt Tuning via Random Projection |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.04501 |