Prompt Consistency for Zero-Shot Task Generalization

Chunting Zhou, Junxian He, Xuezhe Ma, Taylor Berg-Kirkpatrick, Graham Neubig

Abstract
One of the most impressive results of recent NLP history is the ability of pre-trained language models to solve new tasks in a zero-shot setting. To achieve this, NLP tasks are framed as natural language prompts, generating a response indicating the predicted output. Nonetheless, the performance in such settings often lags far behind its supervised counterpart, suggesting a large space for potential improvement. In this paper, we explore methods to utilize unlabeled data to improve zero-shot performance. Specifically, we take advantage of the fact that multiple prompts can be used to specify a single task, and propose to regularize prompt consistency, encouraging consistent predictions over this diverse set of prompts. Our method makes it possible to fine-tune the model either with extra unlabeled training data, or directly on test input at inference time in an unsupervised manner. In experiments, our approach outperforms the state-of-the-art zero-shot learner, T0, on 9 out of 11 datasets across 4 NLP tasks by up to 10.6 absolute points in terms of accuracy. The gains are often attained with a small number of unlabeled examples.
Anthology ID:
2022.findings-emnlp.192
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2613–2626
Language:
URL:
https://preview.aclanthology.org/icon-24-ingestion/2022.findings-emnlp.192/
DOI:
10.18653/v1/2022.findings-emnlp.192
Bibkey:
Cite (ACL):
Chunting Zhou, Junxian He, Xuezhe Ma, Taylor Berg-Kirkpatrick, and Graham Neubig. 2022. Prompt Consistency for Zero-Shot Task Generalization. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2613–2626, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Prompt Consistency for Zero-Shot Task Generalization (Zhou et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/icon-24-ingestion/2022.findings-emnlp.192.pdf
PDF Search Fix data