@inproceedings{zhang-etal-2026-supervised,
title = "Supervised Contrastive Fine-Tuning for Active Few-Shot Learning",
author = "Zhang, Zirui and
Ge, Lei and
Qiao, Shengyu",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.814/",
doi = "10.63317/5p4u2sjsmrcm",
pages = "10365--10375",
abstract = "Active Few-Shot Learning (AFSL) is an effective paradigm for improving the performance of large language models under limited annotation budgets. To address the inefficiency of conventional fine-tuning objectives in AFSL, this paper proposes a supervised contrastive fine-tuning framework specifically designed for natural language processing (NLP) text classification tasks. By integrating Supervised Contrastive Learning (SCL) with Hard Negative Mining (HNM), the proposed framework optimizes the embedding space through an enhanced hybrid loss function, thereby improving the utilization efficiency of labeled samples. Extensive experiments on five benchmark datasets show that, under a fixed state-of-the-art (SOTA) query strategy, our method consistently outperforms baseline models in text classification performance, and exhibits strong generalizability across different backbone architectures and acquisition functions. These findings demonstrate that optimizing how to learn{---}through improved learning objectives{---}provides a complementary direction to existing query strategies in advancing AFSL."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-supervised">
<titleInfo>
<title>Supervised Contrastive Fine-Tuning for Active Few-Shot Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zirui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Ge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengyu</namePart>
<namePart type="family">Qiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Active Few-Shot Learning (AFSL) is an effective paradigm for improving the performance of large language models under limited annotation budgets. To address the inefficiency of conventional fine-tuning objectives in AFSL, this paper proposes a supervised contrastive fine-tuning framework specifically designed for natural language processing (NLP) text classification tasks. By integrating Supervised Contrastive Learning (SCL) with Hard Negative Mining (HNM), the proposed framework optimizes the embedding space through an enhanced hybrid loss function, thereby improving the utilization efficiency of labeled samples. Extensive experiments on five benchmark datasets show that, under a fixed state-of-the-art (SOTA) query strategy, our method consistently outperforms baseline models in text classification performance, and exhibits strong generalizability across different backbone architectures and acquisition functions. These findings demonstrate that optimizing how to learn—through improved learning objectives—provides a complementary direction to existing query strategies in advancing AFSL.</abstract>
<identifier type="citekey">zhang-etal-2026-supervised</identifier>
<identifier type="doi">10.63317/5p4u2sjsmrcm</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.814/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10365</start>
<end>10375</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Supervised Contrastive Fine-Tuning for Active Few-Shot Learning
%A Zhang, Zirui
%A Ge, Lei
%A Qiao, Shengyu
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F zhang-etal-2026-supervised
%X Active Few-Shot Learning (AFSL) is an effective paradigm for improving the performance of large language models under limited annotation budgets. To address the inefficiency of conventional fine-tuning objectives in AFSL, this paper proposes a supervised contrastive fine-tuning framework specifically designed for natural language processing (NLP) text classification tasks. By integrating Supervised Contrastive Learning (SCL) with Hard Negative Mining (HNM), the proposed framework optimizes the embedding space through an enhanced hybrid loss function, thereby improving the utilization efficiency of labeled samples. Extensive experiments on five benchmark datasets show that, under a fixed state-of-the-art (SOTA) query strategy, our method consistently outperforms baseline models in text classification performance, and exhibits strong generalizability across different backbone architectures and acquisition functions. These findings demonstrate that optimizing how to learn—through improved learning objectives—provides a complementary direction to existing query strategies in advancing AFSL.
%R 10.63317/5p4u2sjsmrcm
%U https://aclanthology.org/2026.lrec-1.814/
%U https://doi.org/10.63317/5p4u2sjsmrcm
%P 10365-10375
Markdown (Informal)
[Supervised Contrastive Fine-Tuning for Active Few-Shot Learning](https://aclanthology.org/2026.lrec-1.814/) (Zhang et al., LREC 2026)
ACL