@inproceedings{ahmadnia-etal-2025-active,
title = "Active Few-Shot Learning for Text Classification",
author = "Ahmadnia, Saeed and
Yousefi Jordehi, Arash and
Hosseini Khasheh Heyran, Mahsa and
Mirroshandel, Seyed Abolghasem and
Rambow, Owen and
Caragea, Cornelia",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.340/",
doi = "10.18653/v1/2025.naacl-long.340",
pages = "6677--6694",
ISBN = "979-8-89176-189-6",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmadnia-etal-2025-active">
<titleInfo>
<title>Active Few-Shot Learning for Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saeed</namePart>
<namePart type="family">Ahmadnia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arash</namePart>
<namePart type="family">Yousefi Jordehi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahsa</namePart>
<namePart type="family">Hosseini Khasheh Heyran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Abolghasem</namePart>
<namePart type="family">Mirroshandel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cornelia</namePart>
<namePart type="family">Caragea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">ahmadnia-etal-2025-active</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.340</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.340/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>6677</start>
<end>6694</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Active Few-Shot Learning for Text Classification
%A Ahmadnia, Saeed
%A Yousefi Jordehi, Arash
%A Hosseini Khasheh Heyran, Mahsa
%A Mirroshandel, Seyed Abolghasem
%A Rambow, Owen
%A Caragea, Cornelia
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F ahmadnia-etal-2025-active
%X 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.
%R 10.18653/v1/2025.naacl-long.340
%U https://aclanthology.org/2025.naacl-long.340/
%U https://doi.org/10.18653/v1/2025.naacl-long.340
%P 6677-6694
Markdown (Informal)
[Active Few-Shot Learning for Text Classification](https://aclanthology.org/2025.naacl-long.340/) (Ahmadnia et al., NAACL 2025)
ACL
- Saeed Ahmadnia, Arash Yousefi Jordehi, Mahsa Hosseini Khasheh Heyran, Seyed Abolghasem Mirroshandel, Owen Rambow, and Cornelia Caragea. 2025. Active Few-Shot Learning for Text Classification. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 6677–6694, Albuquerque, New Mexico. Association for Computational Linguistics.