@inproceedings{li-etal-2024-mode-cotd,
title = "{M}o{DE}-{C}o{TD}: Chain-of-Thought Distillation for Complex Reasoning Tasks with Mixture of Decoupled {L}o{RA}-Experts",
author = "Li, Xiang and
He, Shizhu and
Wu, Jiayu and
Yang, Zhao and
Xu, Yao and
Jun, Yang jun and
Liu, Haifeng and
Liu, Kang and
Zhao, Jun",
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.1003",
pages = "11475--11485",
abstract = "Chain-of-thought Distillation (CoTD) aims at distilling Chain-of-thought (CoT) reasoning ability of large language models (LLMs) to much smaller student models. The core of CoTD is using a large teacher model to generate rationales and fine-tune smaller student models. However, current Chain-of-thought Distillation works have the following limitations: 1) Student models are separately distilled from specific reasoning tasks and lack a collaboration mechanism, hindering the enhancement of reasoning performance through collaboration among various reasoning tasks. 2) The parameter update of student models severely harms the CoT reasoning ability on other unseen reasoning tasks not included in the distillation process. In this work, we introduce a novel CoT Distillation method, MoDE-CoTD, which decouples the CoT reasoning abilities out of the student model by distilling multiple LoRA-Experts and freezing the parameters of the student model. Sequentially, LoRA-Experts are combined and adapted to handle both seen and unseen reasoning tasks, enabling collaboration among diverse reasoning tasks to further enhance CoT reasoning performance. Experimental results on 14 datasets (including 4 unseen datasets) demonstrate the strength of MoDE-CoTD, with an average accuracy gain of 6.3{\%} on seen datasets and 7.8{\%} on unseen datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-mode-cotd">
<titleInfo>
<title>MoDE-CoTD: Chain-of-Thought Distillation for Complex Reasoning Tasks with Mixture of Decoupled LoRA-Experts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayu</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">jun</namePart>
<namePart type="family">Jun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haifeng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhao</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>Chain-of-thought Distillation (CoTD) aims at distilling Chain-of-thought (CoT) reasoning ability of large language models (LLMs) to much smaller student models. The core of CoTD is using a large teacher model to generate rationales and fine-tune smaller student models. However, current Chain-of-thought Distillation works have the following limitations: 1) Student models are separately distilled from specific reasoning tasks and lack a collaboration mechanism, hindering the enhancement of reasoning performance through collaboration among various reasoning tasks. 2) The parameter update of student models severely harms the CoT reasoning ability on other unseen reasoning tasks not included in the distillation process. In this work, we introduce a novel CoT Distillation method, MoDE-CoTD, which decouples the CoT reasoning abilities out of the student model by distilling multiple LoRA-Experts and freezing the parameters of the student model. Sequentially, LoRA-Experts are combined and adapted to handle both seen and unseen reasoning tasks, enabling collaboration among diverse reasoning tasks to further enhance CoT reasoning performance. Experimental results on 14 datasets (including 4 unseen datasets) demonstrate the strength of MoDE-CoTD, with an average accuracy gain of 6.3% on seen datasets and 7.8% on unseen datasets.</abstract>
<identifier type="citekey">li-etal-2024-mode-cotd</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1003</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11475</start>
<end>11485</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MoDE-CoTD: Chain-of-Thought Distillation for Complex Reasoning Tasks with Mixture of Decoupled LoRA-Experts
%A Li, Xiang
%A He, Shizhu
%A Wu, Jiayu
%A Yang, Zhao
%A Xu, Yao
%A Jun, Yang jun
%A Liu, Haifeng
%A Liu, Kang
%A Zhao, Jun
%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 li-etal-2024-mode-cotd
%X Chain-of-thought Distillation (CoTD) aims at distilling Chain-of-thought (CoT) reasoning ability of large language models (LLMs) to much smaller student models. The core of CoTD is using a large teacher model to generate rationales and fine-tune smaller student models. However, current Chain-of-thought Distillation works have the following limitations: 1) Student models are separately distilled from specific reasoning tasks and lack a collaboration mechanism, hindering the enhancement of reasoning performance through collaboration among various reasoning tasks. 2) The parameter update of student models severely harms the CoT reasoning ability on other unseen reasoning tasks not included in the distillation process. In this work, we introduce a novel CoT Distillation method, MoDE-CoTD, which decouples the CoT reasoning abilities out of the student model by distilling multiple LoRA-Experts and freezing the parameters of the student model. Sequentially, LoRA-Experts are combined and adapted to handle both seen and unseen reasoning tasks, enabling collaboration among diverse reasoning tasks to further enhance CoT reasoning performance. Experimental results on 14 datasets (including 4 unseen datasets) demonstrate the strength of MoDE-CoTD, with an average accuracy gain of 6.3% on seen datasets and 7.8% on unseen datasets.
%U https://aclanthology.org/2024.lrec-main.1003
%P 11475-11485
Markdown (Informal)
[MoDE-CoTD: Chain-of-Thought Distillation for Complex Reasoning Tasks with Mixture of Decoupled LoRA-Experts](https://aclanthology.org/2024.lrec-main.1003) (Li et al., LREC-COLING 2024)
ACL
- Xiang Li, Shizhu He, Jiayu Wu, Zhao Yang, Yao Xu, Yang jun Jun, Haifeng Liu, Kang Liu, and Jun Zhao. 2024. MoDE-CoTD: Chain-of-Thought Distillation for Complex Reasoning Tasks with Mixture of Decoupled LoRA-Experts. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11475–11485, Torino, Italia. ELRA and ICCL.