Active Few-Shot Learning for Text Classification
This addresses a bottleneck in FSL for NLP practitioners by enhancing sample selection, though it is incremental as it builds on existing FSL and active learning methods.
The paper tackles the problem of poor performance in Few-Shot Learning (FSL) for text classification when unsuitable support samples are chosen, proposing an active learning-based instance selection mechanism that improves FSL performance across five tasks.
The rise of Large Language Models (LLMs) has boosted the use of Few-Shot Learning (FSL) methods in natural language processing, achieving acceptable performance even when working with limited training data. The goal of FSL is to effectively utilize a small number of annotated samples in the learning process. However, the performance of FSL suffers when unsuitable support samples are chosen. This problem arises due to the heavy reliance on a limited number of support samples, which hampers consistent performance improvement even when more support samples are added. To address this challenge, we propose an active learning-based instance selection mechanism that identifies effective support instances from the unlabeled pool and can work with different LLMs. Our experiments on five tasks show that our method frequently improves the performance of FSL. We make our implementation available on GitHub.