Meta-training with Demonstration Retrieval for Efficient Few-shot Learning

TL;DR

This paper introduces a novel meta-training approach that combines demonstration retrieval with parameter-efficient models, significantly improving few-shot learning across multiple NLP tasks while reducing computational requirements.

Contribution

It is the first to integrate retrieval with meta-training, using DPR to retrieve demonstrations from many tasks, enhancing generalization and efficiency in few-shot NLP learning.

Findings

Outperforms existing parameter-efficient and retrieval-augmented methods on QA, NLI, and text classification tasks.

Enables quick meta-training and fine-tuning on a single GPU.

Demonstration retrieval improves model generalization across diverse tasks.

Abstract

Large language models show impressive results on few-shot NLP tasks. However, these models are memory and computation-intensive. Meta-training allows one to leverage smaller models for few-shot generalization in a domain-general and task-agnostic manner; however, these methods alone results in models that may not have sufficient parameterization or knowledge to adapt quickly to a large variety of tasks. To overcome this issue, we propose meta-training with demonstration retrieval, where we use a dense passage retriever to retrieve semantically similar labeled demonstrations to each example for more varied supervision. By separating external knowledge from model parameters, we can use meta-training to train parameter-efficient models that generalize well on a larger variety of tasks. We construct a meta-training set from UnifiedQA and CrossFit, and propose a demonstration bank based on UnifiedQA tasks. To our knowledge, our work is the first to combine retrieval with meta-training, to use DPR models to retrieve demonstrations, and to leverage demonstrations from many tasks simultaneously, rather than randomly sampling demonstrations from the training set of the target task. Our approach outperforms a variety of targeted parameter-efficient and retrieval-augmented few-shot methods on QA, NLI, and text classification tasks (including SQuAD, QNLI, and TREC). Our approach can be meta-trained and fine-tuned quickly on a single GPU.