On Transferability of Prompt Tuning for Natural Language Processing
Prompt tuning (PT) is a promising parameter-efficient method to utilize extremely large pre-trained language models (PLMs), which can achieve comparable performance to full-parameter fine-tuning by only tuning a few soft prompts. However, PT requires much more training time than fine-tuning. Intuitively, knowledge transfer can help to improve the efficiency. To explore whether we can improve PT via prompt transfer, we empirically investigate the transferability of soft prompts across different downstream tasks and PLMs in this work. We find that (1) in zero-shot setting, trained soft prompts can effectively transfer to similar tasks on the same PLM and also to other PLMs with a cross-model projector trained on similar tasks; (2) when used as initialization, trained soft prompts of similar tasks and projected prompts of other PLMs can significantly accelerate training and also improve the performance of PT. Moreover, to explore what decides prompt transferability, we investigate various transferability indicators and find that the overlapping rate of activated neurons strongly reflects the transferability, which suggests how the prompts stimulate PLMs is essential. Our findings show that prompt transfer is promising for improving PT, and further research shall focus more on prompts' stimulation to PLMs. The source code can be obtained from https://github.com/thunlp/Prompt-Transferability.
Code (1)
Tasks
Natural Language UnderstandingTransfer LearningSimilar Papers 제목 키워드 기반
On Transferability of Prompt Tuning for Natural Language Processing
Prompt tuning (PT) is a promising parameter-efficient method to utilize extremely large pre-trained language models (PLMs), which can achieve comparable performance to full-parameter fine-tuning by only tuning a few soft…
Transfer LearningLearning to Compress Prompt in Natural Language Formats
Large language models (LLMs) are great at processing multiple natural language processing tasks, but their abilities are constrained by inferior performance with long context, slow inference speed, and the high cost of c…
Chain of Thought Prompt Tuning in Vision Language Models
Language-Image Pre-training has demonstrated promising results on zero-shot and few-shot downstream tasks by prompting visual models with natural language prompts. However, most recent studies only use a single prompt fo…
Domain Generalizationimage-classificationImage ClassificationLanguage Modeling+4Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models
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 prom…
A Parameter-Efficient Transfer Learning Approach through Multitask Prompt Distillation and Decomposition for Clinical NLP
Existing prompt-based fine-tuning methods typically learn task-specific prompts independently, imposing significant computing and storage overhead at scale when deploying multiple clinical natural language processing (NL…
Natural Language InferenceRelation ExtractionQuestion AnsweringTransfer Learning