Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation
This work addresses the sample inefficiency of prompt tuning for NLP practitioners, offering a domain adaptation approach that enhances transferability and performance in data-scarce scenarios.
The paper tackled the problem of prompt tuning requiring large datasets by proposing a domain adaptation method called OPTIMA, which uses unlabeled target domain data during pretraining to regularize decision boundaries, resulting in significantly improved sample efficiency and outperforming full-model tuning in few-shot settings.
Prompt tuning, or the conditioning of a frozen pretrained language model (PLM) with soft prompts learned from data, has demonstrated impressive performance on a wide range of NLP tasks. However, prompt tuning requires a large training dataset to be effective and is outperformed by finetuning the entire PLM in data-scarce regimes. Previous work (Gu et al., 2022, Vu et al., 2022) proposed to transfer soft prompts pretrained on the source domain to the target domain. In this paper, we explore domain adaptation for prompt tuning, a problem setting where unlabeled data from the target domain are available during pretraining. We propose bOosting Prompt TunIng with doMain Adaptation (OPTIMA), which regularizes the decision boundary to be smooth around regions where source and target data distributions are similar. Extensive experiments demonstrate that OPTIMA significantly enhances the transferability and sample-efficiency of prompt tuning compared to strong baselines. Moreover, in few-shot settings, OPTIMA exceeds full-model tuning by a large margin.