@inproceedings{xu-etal-2024-adaptive-reinforcement,
title = "Adaptive Reinforcement Tuning Language Models as Hard Data Generators for Sentence Representation",
author = "Xu, Bo and
Wu, Yifei and
Wei, Shouang and
Du, Ming and
Wang, Hongya",
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.33",
pages = "358--371",
abstract = "Sentence representation learning is a fundamental task in NLP. Existing methods use contrastive learning (CL) to learn effective sentence representations, which benefit from high-quality contrastive data but require extensive human annotation. Large language models (LLMs) like ChatGPT and GPT4 can automatically generate such data. However, this alternative strategy also encounters challenges: 1) obtaining high-quality generated data from small-parameter LLMs is difficult, and 2) inefficient utilization of the generated data. To address these challenges, we propose a novel adaptive reinforcement tuning (ART) framework. Specifically, to address the first challenge, we introduce a reinforcement learning approach for fine-tuning small-parameter LLMs, enabling the generation of high-quality hard contrastive data without human feedback. To address the second challenge, we propose an adaptive iterative framework to guide the small-parameter LLMs to generate progressively harder samples through multiple iterations, thereby maximizing the utility of generated data. Experiments conducted on seven semantic text similarity tasks demonstrate that the sentence representation models trained using the synthetic data generated by our proposed method achieve state-of-the-art performance. Our code is available at https://github.com/WuNein/AdaptCL.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2024-adaptive-reinforcement">
<titleInfo>
<title>Adaptive Reinforcement Tuning Language Models as Hard Data Generators for Sentence Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shouang</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongya</namePart>
<namePart type="family">Wang</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>Sentence representation learning is a fundamental task in NLP. Existing methods use contrastive learning (CL) to learn effective sentence representations, which benefit from high-quality contrastive data but require extensive human annotation. Large language models (LLMs) like ChatGPT and GPT4 can automatically generate such data. However, this alternative strategy also encounters challenges: 1) obtaining high-quality generated data from small-parameter LLMs is difficult, and 2) inefficient utilization of the generated data. To address these challenges, we propose a novel adaptive reinforcement tuning (ART) framework. Specifically, to address the first challenge, we introduce a reinforcement learning approach for fine-tuning small-parameter LLMs, enabling the generation of high-quality hard contrastive data without human feedback. To address the second challenge, we propose an adaptive iterative framework to guide the small-parameter LLMs to generate progressively harder samples through multiple iterations, thereby maximizing the utility of generated data. Experiments conducted on seven semantic text similarity tasks demonstrate that the sentence representation models trained using the synthetic data generated by our proposed method achieve state-of-the-art performance. Our code is available at https://github.com/WuNein/AdaptCL.</abstract>
<identifier type="citekey">xu-etal-2024-adaptive-reinforcement</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.33</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>358</start>
<end>371</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adaptive Reinforcement Tuning Language Models as Hard Data Generators for Sentence Representation
%A Xu, Bo
%A Wu, Yifei
%A Wei, Shouang
%A Du, Ming
%A Wang, Hongya
%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 xu-etal-2024-adaptive-reinforcement
%X Sentence representation learning is a fundamental task in NLP. Existing methods use contrastive learning (CL) to learn effective sentence representations, which benefit from high-quality contrastive data but require extensive human annotation. Large language models (LLMs) like ChatGPT and GPT4 can automatically generate such data. However, this alternative strategy also encounters challenges: 1) obtaining high-quality generated data from small-parameter LLMs is difficult, and 2) inefficient utilization of the generated data. To address these challenges, we propose a novel adaptive reinforcement tuning (ART) framework. Specifically, to address the first challenge, we introduce a reinforcement learning approach for fine-tuning small-parameter LLMs, enabling the generation of high-quality hard contrastive data without human feedback. To address the second challenge, we propose an adaptive iterative framework to guide the small-parameter LLMs to generate progressively harder samples through multiple iterations, thereby maximizing the utility of generated data. Experiments conducted on seven semantic text similarity tasks demonstrate that the sentence representation models trained using the synthetic data generated by our proposed method achieve state-of-the-art performance. Our code is available at https://github.com/WuNein/AdaptCL.
%U https://aclanthology.org/2024.lrec-main.33
%P 358-371
Markdown (Informal)
[Adaptive Reinforcement Tuning Language Models as Hard Data Generators for Sentence Representation](https://aclanthology.org/2024.lrec-main.33) (Xu et al., LREC-COLING 2024)
ACL