MetaPrompting: Learning to Learn Better Prompts

Yutai Hou, Hongyuan Dong, Xinghao Wang, Bohan Li, Wanxiang Che


Abstract
Prompting method is regarded as one of the crucial progress for few-shot nature language processing. Recent research on prompting moves from discrete tokens based “hard prompts” to continuous “soft prompts”, which employ learnable vectors as pseudo prompt tokens and achieve better performance. Though showing promising prospects, these soft-prompting methods are observed to rely heavily on good initialization to take effect. Unfortunately, obtaining a perfect initialization for soft prompts requires understanding of inner language models working and elaborate design, which is no easy task and has to restart from scratch for each new task. To remedy this, we propose a generalized soft prompting method called MetaPrompting, which adopts the well-recognized model-agnostic meta-learning algorithm to automatically find better prompt initialization that facilitates fast adaptation to new prompting tasks. Extensive experiments show MetaPrompting tackles soft prompt initialization problem and brings significant improvement on three different datasets (over 6 points improvement in accuracy for 1-shot setting), achieving new state-of-the-art performance.
Anthology ID:
2022.coling-1.287
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
3251–3262
Language:
URL:
https://aclanthology.org/2022.coling-1.287
DOI:
Bibkey:
Cite (ACL):
Yutai Hou, Hongyuan Dong, Xinghao Wang, Bohan Li, and Wanxiang Che. 2022. MetaPrompting: Learning to Learn Better Prompts. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3251–3262, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
MetaPrompting: Learning to Learn Better Prompts (Hou et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.287.pdf