# Active Few-Shot Learning for Text Classification

arXiv: https://arxiv.org/abs/2502.18782 · HTML: https://mlsanity.com/paper/2502.18782/

## 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 (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Meta-Transfer Learning for Few-Shot Learning](https://mlsanity.com/paper/1812.02391/) (2018)
- [Few-shot Learning with Multilingual Language Models](https://mlsanity.com/paper/2112.10668/) (2021)
- [Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning](https://mlsanity.com/paper/2011.01403/) (2020)
- [The Multilingual Amazon Reviews Corpus](https://mlsanity.com/paper/2010.02573/) (2020)
- [Few-Shot Text Generation with Pattern-Exploiting Training](https://mlsanity.com/paper/2012.11926/) (2020)
- [Few-Shot NLG with Pre-Trained Language Model](https://mlsanity.com/paper/1904.09521/) (2019)
- [PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models](https://mlsanity.com/paper/2204.01172/) (2022)
- [Language Models for Text Classification: Is In-Context Learning Enough?](https://mlsanity.com/paper/2403.17661/) (2024)
- [On Training Instance Selection for Few-Shot Neural Text Generation](https://mlsanity.com/paper/2107.03176/) (2021)
- [Revisiting Self-Training for Few-Shot Learning of Language Model](https://mlsanity.com/paper/2110.01256/) (2021)
- [Active Few-Shot Learning with FASL](https://mlsanity.com/paper/2204.09347/) (2022)

## Built on by (most cited first, 6 of 6)

- [CrowdAgent: Multi-Agent Managed Multi-Source Annotation System](https://mlsanity.com/paper/2509.14030/) (2025)
- [Select, Label, Evaluate: Active Testing in NLP](https://mlsanity.com/paper/2603.21840/) (2026)
- [Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs](https://mlsanity.com/paper/2510.03762/) (2025)
- [Small sample-based adaptive text classification through iterative and contrastive description refinement](https://mlsanity.com/paper/2508.00957/) (2025)
- [From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse](https://mlsanity.com/paper/2509.14712/) (2025)
- [Neuron-Aware Active Few-Shot Learning for LLMs](https://mlsanity.com/paper/2607.02423/) (2026)

## 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.