@inproceedings{zhang-etal-2024-la-ucl,
title = "{LA}-{UCL}: {LLM}-Augmented Unsupervised Contrastive Learning Framework for Few-Shot Text Classification",
author = "Zhang, Jing and
Gao, Hui and
Zhang, Peng and
Feng, Boda and
Deng, Wenmin and
Hou, Yuexian",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.890",
pages = "10198--10207",
abstract = "The few-shot tasks require the model to have the ability to generalize from a few samples. However, due to the lack of cognitive ability, the current works cannot fully utilize limited samples to expand the sample space and still suffer from overfitting issues. To address the problems, we propose a LLM-Augmented Unsupervised Contrastive Learning Framework (LA-UCL), which introduces a cognition-enabled Large Language Model (LLM) for efficient data augmentation, and presents corresponding contrastive learning strategies. Specifically, in the self-augmented contrastive learning module, we construct a retrieval-based in-context prompt scheme by retrieving similar but different category data from the original samples, guiding the LLM to generate more discriminative augmented data. Then, by designing group-level contrastive loss to enhance the model{'}s discriminative ability. In the external-augmented contrastive learning module, we utilize web knowledge retrieval to expand the sample space and leverage LLM to generate more diverse data, and introduce sample-level contrastive loss for unlabeled data to improve the model{'}s generalization. Experimental results on six datasets show that our model exceeds the baseline models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-la-ucl">
<titleInfo>
<title>LA-UCL: LLM-Augmented Unsupervised Contrastive Learning Framework for Few-Shot Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boda</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenmin</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuexian</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The few-shot tasks require the model to have the ability to generalize from a few samples. However, due to the lack of cognitive ability, the current works cannot fully utilize limited samples to expand the sample space and still suffer from overfitting issues. To address the problems, we propose a LLM-Augmented Unsupervised Contrastive Learning Framework (LA-UCL), which introduces a cognition-enabled Large Language Model (LLM) for efficient data augmentation, and presents corresponding contrastive learning strategies. Specifically, in the self-augmented contrastive learning module, we construct a retrieval-based in-context prompt scheme by retrieving similar but different category data from the original samples, guiding the LLM to generate more discriminative augmented data. Then, by designing group-level contrastive loss to enhance the model’s discriminative ability. In the external-augmented contrastive learning module, we utilize web knowledge retrieval to expand the sample space and leverage LLM to generate more diverse data, and introduce sample-level contrastive loss for unlabeled data to improve the model’s generalization. Experimental results on six datasets show that our model exceeds the baseline models.</abstract>
<identifier type="citekey">zhang-etal-2024-la-ucl</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.890</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10198</start>
<end>10207</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LA-UCL: LLM-Augmented Unsupervised Contrastive Learning Framework for Few-Shot Text Classification
%A Zhang, Jing
%A Gao, Hui
%A Zhang, Peng
%A Feng, Boda
%A Deng, Wenmin
%A Hou, Yuexian
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zhang-etal-2024-la-ucl
%X The few-shot tasks require the model to have the ability to generalize from a few samples. However, due to the lack of cognitive ability, the current works cannot fully utilize limited samples to expand the sample space and still suffer from overfitting issues. To address the problems, we propose a LLM-Augmented Unsupervised Contrastive Learning Framework (LA-UCL), which introduces a cognition-enabled Large Language Model (LLM) for efficient data augmentation, and presents corresponding contrastive learning strategies. Specifically, in the self-augmented contrastive learning module, we construct a retrieval-based in-context prompt scheme by retrieving similar but different category data from the original samples, guiding the LLM to generate more discriminative augmented data. Then, by designing group-level contrastive loss to enhance the model’s discriminative ability. In the external-augmented contrastive learning module, we utilize web knowledge retrieval to expand the sample space and leverage LLM to generate more diverse data, and introduce sample-level contrastive loss for unlabeled data to improve the model’s generalization. Experimental results on six datasets show that our model exceeds the baseline models.
%U https://aclanthology.org/2024.lrec-main.890
%P 10198-10207
Markdown (Informal)
[LA-UCL: LLM-Augmented Unsupervised Contrastive Learning Framework for Few-Shot Text Classification](https://aclanthology.org/2024.lrec-main.890) (Zhang et al., LREC-COLING 2024)
ACL