Active Few-Shot Learning for Text Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ahmadnia, Saeed, Jordehi, Arash Yousefi, Heyran, Mahsa Hosseini Khasheh, Mirroshandel, Seyed Abolghasem, Rambow, Owen, Caragea, Cornelia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913707576000512
author Ahmadnia, Saeed
Jordehi, Arash Yousefi
Heyran, Mahsa Hosseini Khasheh
Mirroshandel, Seyed Abolghasem
Rambow, Owen
Caragea, Cornelia
author_facet Ahmadnia, Saeed
Jordehi, Arash Yousefi
Heyran, Mahsa Hosseini Khasheh
Mirroshandel, Seyed Abolghasem
Rambow, Owen
Caragea, Cornelia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_18782
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Active Few-Shot Learning for Text Classification
Ahmadnia, Saeed
Jordehi, Arash Yousefi
Heyran, Mahsa Hosseini Khasheh
Mirroshandel, Seyed Abolghasem
Rambow, Owen
Caragea, Cornelia
Computation and Language
I.2.7
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.
title Active Few-Shot Learning for Text Classification
topic Computation and Language
I.2.7
url https://arxiv.org/abs/2502.18782