@inproceedings{lee-etal-2024-radcot,
title = "{RADC}o{T}: Retrieval-Augmented Distillation to Specialization Models for Generating Chain-of-Thoughts in Query Expansion",
author = "Lee, Sung-Min and
Park, Eunhwan and
Jeon, DongHyeon and
Kang, Inho and
Na, Seung-Hoon",
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.1182",
pages = "13514--13523",
abstract = "Large language models (LLMs) have demonstrated superior performance to that of small language models (SLM) in information retrieval for various subtasks including dense retrieval, reranking, query expansion, and pseudo-document generation. However, the parameter sizes of LLMs are extremely large, making it expensive to operate LLMs stably for providing LLM-based retrieval services. Recently, retrieval-augmented language models have been widely employed to significantly reduce the parameter size by retrieving relevant knowledge from large-scale corpora and exploiting the resulting {``}in-context{''} knowledge as additional model input, thereby substantially reducing the burden of internalizing and retaining world knowledge in model parameters. Armed by the retrieval-augmented language models, we present a retrieval-augmented model specialization that distills the capability of LLMs to generate the chain-of-thoughts (CoT) for query expansion {--} that is, injects the LLM{'}s capability to generate CoT into a retrieval-augmented SLM {--} referred to as \textbf{RADCoT}. Experimental results on the MS-MARCO, TREC DL 19, 20 datasets show that RADCoT yields consistent improvements over distillation without retrieval, achieving comparable performance to that of the query expansion method using LLM-based CoTs. Our code is publicly available at \url{https://github.com/ZIZUN/RADCoT}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2024-radcot">
<titleInfo>
<title>RADCoT: Retrieval-Augmented Distillation to Specialization Models for Generating Chain-of-Thoughts in Query Expansion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sung-Min</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunhwan</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">DongHyeon</namePart>
<namePart type="family">Jeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inho</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</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>Large language models (LLMs) have demonstrated superior performance to that of small language models (SLM) in information retrieval for various subtasks including dense retrieval, reranking, query expansion, and pseudo-document generation. However, the parameter sizes of LLMs are extremely large, making it expensive to operate LLMs stably for providing LLM-based retrieval services. Recently, retrieval-augmented language models have been widely employed to significantly reduce the parameter size by retrieving relevant knowledge from large-scale corpora and exploiting the resulting “in-context” knowledge as additional model input, thereby substantially reducing the burden of internalizing and retaining world knowledge in model parameters. Armed by the retrieval-augmented language models, we present a retrieval-augmented model specialization that distills the capability of LLMs to generate the chain-of-thoughts (CoT) for query expansion – that is, injects the LLM’s capability to generate CoT into a retrieval-augmented SLM – referred to as RADCoT. Experimental results on the MS-MARCO, TREC DL 19, 20 datasets show that RADCoT yields consistent improvements over distillation without retrieval, achieving comparable performance to that of the query expansion method using LLM-based CoTs. Our code is publicly available at https://github.com/ZIZUN/RADCoT.</abstract>
<identifier type="citekey">lee-etal-2024-radcot</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1182</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13514</start>
<end>13523</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RADCoT: Retrieval-Augmented Distillation to Specialization Models for Generating Chain-of-Thoughts in Query Expansion
%A Lee, Sung-Min
%A Park, Eunhwan
%A Jeon, DongHyeon
%A Kang, Inho
%A Na, Seung-Hoon
%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 lee-etal-2024-radcot
%X Large language models (LLMs) have demonstrated superior performance to that of small language models (SLM) in information retrieval for various subtasks including dense retrieval, reranking, query expansion, and pseudo-document generation. However, the parameter sizes of LLMs are extremely large, making it expensive to operate LLMs stably for providing LLM-based retrieval services. Recently, retrieval-augmented language models have been widely employed to significantly reduce the parameter size by retrieving relevant knowledge from large-scale corpora and exploiting the resulting “in-context” knowledge as additional model input, thereby substantially reducing the burden of internalizing and retaining world knowledge in model parameters. Armed by the retrieval-augmented language models, we present a retrieval-augmented model specialization that distills the capability of LLMs to generate the chain-of-thoughts (CoT) for query expansion – that is, injects the LLM’s capability to generate CoT into a retrieval-augmented SLM – referred to as RADCoT. Experimental results on the MS-MARCO, TREC DL 19, 20 datasets show that RADCoT yields consistent improvements over distillation without retrieval, achieving comparable performance to that of the query expansion method using LLM-based CoTs. Our code is publicly available at https://github.com/ZIZUN/RADCoT.
%U https://aclanthology.org/2024.lrec-main.1182
%P 13514-13523
Markdown (Informal)
[RADCoT: Retrieval-Augmented Distillation to Specialization Models for Generating Chain-of-Thoughts in Query Expansion](https://aclanthology.org/2024.lrec-main.1182) (Lee et al., LREC-COLING 2024)
ACL