Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Zijun, Wu, Yongkang, Mou, Lili
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911953429987328
author Wu, Zijun
Wu, Yongkang
Mou, Lili
author_facet Wu, Zijun
Wu, Yongkang
Mou, Lili
contents Prompt tuning in natural language processing (NLP) has become an increasingly popular method for adapting large language models to specific tasks. However, the transferability of these prompts, especially continuous prompts, between different models remains a challenge. In this work, we propose a zero-shot continuous prompt transfer method, where source prompts are encoded into relative space and the corresponding target prompts are searched for transferring to target models. Experimental results confirm the effectiveness of our method, showing that 'task semantics' in continuous prompts can be generalized across various language models. Moreover, we find that combining 'task semantics' from multiple source models can further enhance the generalizability of transfer.
format Preprint
id arxiv_https___arxiv_org_abs_2310_01691
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models
Wu, Zijun
Wu, Yongkang
Mou, Lili
Computation and Language
Artificial Intelligence
Prompt tuning in natural language processing (NLP) has become an increasingly popular method for adapting large language models to specific tasks. However, the transferability of these prompts, especially continuous prompts, between different models remains a challenge. In this work, we propose a zero-shot continuous prompt transfer method, where source prompts are encoded into relative space and the corresponding target prompts are searched for transferring to target models. Experimental results confirm the effectiveness of our method, showing that 'task semantics' in continuous prompts can be generalized across various language models. Moreover, we find that combining 'task semantics' from multiple source models can further enhance the generalizability of transfer.
title Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2310.01691