On Transferability of Prompt Tuning for Natural Language Processing

Yusheng Su, Xiaozhi Wang, Yujia Qin, Chi-Min Chan, Yankai Lin, Huadong Wang, Kaiyue Wen, Zhiyuan Liu, Peng Li, Juanzi Li, Lei Hou, Maosong Sun, Jie Zhou


Abstract
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.
Anthology ID:
2022.naacl-main.290
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3949–3969
Language:
URL:
https://aclanthology.org/2022.naacl-main.290
DOI:
10.18653/v1/2022.naacl-main.290
Bibkey:
Cite (ACL):
Yusheng Su, Xiaozhi Wang, Yujia Qin, Chi-Min Chan, Yankai Lin, Huadong Wang, Kaiyue Wen, Zhiyuan Liu, Peng Li, Juanzi Li, Lei Hou, Maosong Sun, and Jie Zhou. 2022. On Transferability of Prompt Tuning for Natural Language Processing. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3949–3969, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
On Transferability of Prompt Tuning for Natural Language Processing (Su et al., NAACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/2022.naacl-main.290.pdf
Video:
 https://preview.aclanthology.org/remove-xml-comments/2022.naacl-main.290.mp4
Code
 thunlp/Prompt-Transferability
Data
GLUEIMDb Movie ReviewsMRPCMulti-NewsMultiNLIQNLISAMSum CorpusSNLISQuADSST