Active Few-Shot Learning for Text Classification

Saeed Ahmadnia, Arash Yousefi Jordehi, Mahsa Hosseini Khasheh Heyran, Seyed Abolghasem Mirroshandel, Owen Rambow +1 more
2/26/2025
cs.CL

No official code found. Best implementation: theSaeed/active-fewshot-learning (4 stars, MIT, last commit 2025-03-17).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

theSaeed/active-fewshot-learningCommunity73%
MIT

[NAACL 2025] Official repository of "Active Few-Shot Learning for Text Classification"

41Python, Jupyter NotebookFeb 3, 20251 years agoMIT

Similar Papers

Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data

87% match2024

ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarios

86% match2024

Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification

85% match1 repo12024

Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models

84% match2024

The Few-shot Dilemma: Over-prompting Large Language Models

84% match2025

Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor Generation and Classification Reframing

83% match2024

Cite this paper

@article{ahmadnia2025active,
  title  = {Active Few-Shot Learning for Text Classification},
  author = {Saeed Ahmadnia and Arash Yousefi Jordehi and Mahsa Hosseini Khasheh Heyran and Seyed Abolghasem Mirroshandel and Owen Rambow and Cornelia Caragea},
  year   = {2025},
  eprint = {2502.18782},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.18782v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.18782.svg)](https://codeofpaper.com/paper/2502.18782)

Discussion