@inproceedings{huang-xiong-2024-it2acl-learning,
title = "{IT}2{ACL} Learning Easy-to-Hard Instructions via 2-Phase Automated Curriculum Learning for Large Language Models",
author = "Huang, Yufei and
Xiong, Deyi",
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.822",
pages = "9405--9421",
abstract = "Instruction tuning has demonstrated its superiority in unlocking the abilities of pre-trained large language models (LLMs), including their capability to respond to diverse human instructions and conduct complex reasoning. In order to further enhance the continuous learning capabilities of pre-trained LLMs, we explore the training process of instruction tuning through the lens of task sequences. We propose a 2-phase automated curriculum learning guided instruction tuning framework, IT2ACL that learns easy-to-hard instructions for LLMs in a self-adjusting dynamic manner. To facilitate curriculum learning from instructions, we propose a loss-driven progress signal for two-phase strategies: instruction prediction gain that decides the instruction level syllabus. Through comprehensive experiments on 70 Chinese datasets which have been grouped into 16 distinct task clusters, we demonstrate the effectiveness of our approach in eliciting latent ability in pre-trained LLMs and achieving superior performance across diverse tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-xiong-2024-it2acl-learning">
<titleInfo>
<title>IT2ACL Learning Easy-to-Hard Instructions via 2-Phase Automated Curriculum Learning for Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yufei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</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>Instruction tuning has demonstrated its superiority in unlocking the abilities of pre-trained large language models (LLMs), including their capability to respond to diverse human instructions and conduct complex reasoning. In order to further enhance the continuous learning capabilities of pre-trained LLMs, we explore the training process of instruction tuning through the lens of task sequences. We propose a 2-phase automated curriculum learning guided instruction tuning framework, IT2ACL that learns easy-to-hard instructions for LLMs in a self-adjusting dynamic manner. To facilitate curriculum learning from instructions, we propose a loss-driven progress signal for two-phase strategies: instruction prediction gain that decides the instruction level syllabus. Through comprehensive experiments on 70 Chinese datasets which have been grouped into 16 distinct task clusters, we demonstrate the effectiveness of our approach in eliciting latent ability in pre-trained LLMs and achieving superior performance across diverse tasks.</abstract>
<identifier type="citekey">huang-xiong-2024-it2acl-learning</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.822</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9405</start>
<end>9421</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IT2ACL Learning Easy-to-Hard Instructions via 2-Phase Automated Curriculum Learning for Large Language Models
%A Huang, Yufei
%A Xiong, Deyi
%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 huang-xiong-2024-it2acl-learning
%X Instruction tuning has demonstrated its superiority in unlocking the abilities of pre-trained large language models (LLMs), including their capability to respond to diverse human instructions and conduct complex reasoning. In order to further enhance the continuous learning capabilities of pre-trained LLMs, we explore the training process of instruction tuning through the lens of task sequences. We propose a 2-phase automated curriculum learning guided instruction tuning framework, IT2ACL that learns easy-to-hard instructions for LLMs in a self-adjusting dynamic manner. To facilitate curriculum learning from instructions, we propose a loss-driven progress signal for two-phase strategies: instruction prediction gain that decides the instruction level syllabus. Through comprehensive experiments on 70 Chinese datasets which have been grouped into 16 distinct task clusters, we demonstrate the effectiveness of our approach in eliciting latent ability in pre-trained LLMs and achieving superior performance across diverse tasks.
%U https://aclanthology.org/2024.lrec-main.822
%P 9405-9421
Markdown (Informal)
[IT2ACL Learning Easy-to-Hard Instructions via 2-Phase Automated Curriculum Learning for Large Language Models](https://aclanthology.org/2024.lrec-main.822) (Huang & Xiong, LREC-COLING 2024)
ACL