mlsanityData to 14 Oct 2026

Active Few-Shot Learning for Text Classification

arXiv 2502.18782 ↗First posted 26 Feb 2025cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

21 of 33 references.

References · 21

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  3. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  4. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  5. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  6. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  7. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,102
  8. 2019A Closer Look at Few-shot Classificationcited by 684
  9. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 669
  10. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  11. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  12. 2021Few-shot Learning with Multilingual Language Modelscited by 278
9 more
  1. 2020Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningcited by 276
  2. 2020The Multilingual Amazon Reviews Corpuscited by 143
  3. 2020Few-Shot Text Generation with Pattern-Exploiting Trainingcited by 87
  4. 2019Few-Shot NLG with Pre-Trained Language Modelcited by 52
  5. 2022PERFECT: Prompt-free and Efficient Few-shot Learning with Language Modelscited by 40
  6. 2024Language Models for Text Classification: Is In-Context Learning Enough?cited by 40
  7. 2021On Training Instance Selection for Few-Shot Neural Text Generationcited by 26
  8. 2021Revisiting Self-Training for Few-Shot Learning of Language Modelcited by 23
  9. 2022Active Few-Shot Learning with FASLcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025CrowdAgent: Multi-Agent Managed Multi-Source Annotation Systemcited by 5
  2. 2026Select, Label, Evaluate: Active Testing in NLPcited by 3
  3. 2025Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMscited by 1
  4. 2025Small sample-based adaptive text classification through iterative and contrastive description refinementcited by 0
  5. 2025From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discoursecited by 0
  6. 2026Neuron-Aware Active Few-Shot Learning for LLMscited by 0