Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuningDownload PDF

Published: 01 Feb 2023, Last Modified: 28 Feb 2023ICLR 2023 posterReaders: Everyone
Keywords: prompt tuning, natural language processing, few-shot learning
TL;DR: For improving few-shot prompt tuning, we propose a Sample-specific Ensemble of Source Models to transfer knowledge from soft prompts trained on source tasks to target tasks by adjusting the contribution of source models for each target sample.
Abstract: Prompt tuning approaches, which learn task-specific soft prompts for a downstream task conditioning on frozen pre-trained models, have attracted growing interest due to its parameter efficiency. With large language models and sufficient training data, prompt tuning performs comparably to full-model tuning. However, with limited training samples in few-shot settings, prompt tuning fails to match the performance of full-model fine-tuning. In this work, we focus on improving the few-shot performance of prompt tuning by transferring knowledge from soft prompts of source tasks with abundant training samples. Recognizing the good generalization capabilities of ensemble methods in low-data regime, we first experiment and show that a simple ensemble of model predictions based on different source prompts, outperforms existing multi-prompt knowledge transfer approaches such as source prompt fusion in the few-shot setting. Motivated by this observation, we further investigate model ensembles and propose Sample-specific Ensemble of Source Models (SESoM). SESoM learns to adjust the contribution of each source model for each target sample separately when ensembling source model outputs. Through this way, SESoM inherits the superior generalization of ensemble methods and simultaneously captures the sample-specific competence of each source prompt. We conduct experiments across a diverse set of eight NLP tasks using models of different scales (T5-\{base, large, XL\}) and find that SESoM consistently outperforms the existing models of the same as well as larger parametric scale by a large margin.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)
10 Replies

Loading