@inproceedings{zhang-etal-2024-generation,
title = "Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following {LLM}",
author = "Zhang, Ruohong and
Wang, Yau-Shian and
Yang, Yiming",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.39",
pages = "659--673",
abstract = "The remarkable performance of large language models (LLMs) in zero-shot language understanding has garnered significant attention.However, employing LLMs for large-scale inference or domain-specific fine-tuning requires immense computational resources due to their substantial model size. To overcome these limitations, we introduce a novel method, namely GenCo, which leverages the strong generative power of LLMs to assist in training a smaller and more adaptable language model. In our method, an LLM plays an important role in the self-training loop of a smaller model in two important ways. Firstly, we utilize an LLM to generate multiple augmented texts for each input instance to enhance its semantic meaning for better understanding. Secondly, we additionally generate high-quality training instances conditioned on predicted labels, ensuring the generated texts are relevant to the labels. In this way, GenCo not only corrects the errors of predicted labels during self-training but also eliminates the need for extensive unlabeled texts. In our experiments, GenCo outperforms previous state-of-the-art methods when only limited ($<5\%$ of original) in-domain text data is available. Notably, our approach surpasses Alpaca-7B with human instructions, highlighting the significance of self-training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-generation">
<titleInfo>
<title>Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruohong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yau-Shian</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The remarkable performance of large language models (LLMs) in zero-shot language understanding has garnered significant attention.However, employing LLMs for large-scale inference or domain-specific fine-tuning requires immense computational resources due to their substantial model size. To overcome these limitations, we introduce a novel method, namely GenCo, which leverages the strong generative power of LLMs to assist in training a smaller and more adaptable language model. In our method, an LLM plays an important role in the self-training loop of a smaller model in two important ways. Firstly, we utilize an LLM to generate multiple augmented texts for each input instance to enhance its semantic meaning for better understanding. Secondly, we additionally generate high-quality training instances conditioned on predicted labels, ensuring the generated texts are relevant to the labels. In this way, GenCo not only corrects the errors of predicted labels during self-training but also eliminates the need for extensive unlabeled texts. In our experiments, GenCo outperforms previous state-of-the-art methods when only limited (<5% of original) in-domain text data is available. Notably, our approach surpasses Alpaca-7B with human instructions, highlighting the significance of self-training.</abstract>
<identifier type="citekey">zhang-etal-2024-generation</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.39</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>659</start>
<end>673</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM
%A Zhang, Ruohong
%A Wang, Yau-Shian
%A Yang, Yiming
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F zhang-etal-2024-generation
%X The remarkable performance of large language models (LLMs) in zero-shot language understanding has garnered significant attention.However, employing LLMs for large-scale inference or domain-specific fine-tuning requires immense computational resources due to their substantial model size. To overcome these limitations, we introduce a novel method, namely GenCo, which leverages the strong generative power of LLMs to assist in training a smaller and more adaptable language model. In our method, an LLM plays an important role in the self-training loop of a smaller model in two important ways. Firstly, we utilize an LLM to generate multiple augmented texts for each input instance to enhance its semantic meaning for better understanding. Secondly, we additionally generate high-quality training instances conditioned on predicted labels, ensuring the generated texts are relevant to the labels. In this way, GenCo not only corrects the errors of predicted labels during self-training but also eliminates the need for extensive unlabeled texts. In our experiments, GenCo outperforms previous state-of-the-art methods when only limited (<5% of original) in-domain text data is available. Notably, our approach surpasses Alpaca-7B with human instructions, highlighting the significance of self-training.
%U https://aclanthology.org/2024.eacl-long.39
%P 659-673
Markdown (Informal)
[Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM](https://aclanthology.org/2024.eacl-long.39) (Zhang et al., EACL 2024)
ACL