@inproceedings{liang-etal-2024-llm,
title = "{LLM}-{REDIAL}: A Large-Scale Dataset for Conversational Recommender Systems Created from User Behaviors with {LLM}s",
author = "Liang, Tingting and
Jin, Chenxin and
Wang, Lingzhi and
Fan, Wenqi and
Xia, Congying and
Chen, Kai and
Yin, Yuyu",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.529",
doi = "10.18653/v1/2024.findings-acl.529",
pages = "8926--8939",
abstract = "The large-scale conversational recommendation dataset is pivotal for the development of conversational recommender systems (CRS). Most existing CRS datasets suffers from the problems of data inextensibility and semantic inconsistency. To tackle these limitations and establish a benchmark in the conversational recommendation scenario, in this paper, we introduce the LLM-REDIAL dataset to facilitate the research in CRS. LLM-REDIAL is constructed by leveraging large language models (LLMs) to generate the high-quality dialogues. To provide the LLMs with detailed guidance, we integrate historical user behavior data with dialogue templates that are carefully designed through the combination of multiple pre-defined goals. LLM-REDIAL has two main advantages. First, it is the largest multi-domain CRS dataset which consists of 47.6k multi-turn dialogues with 482.6k utterances across 4 domains. Second, dialogue semantics and the users{'} historical interaction information is highly consistent. Human evaluation are conducted to verify the quality of LLM-REDIAL. In addition, we evaluate the usability of advanced LLM-based models on LLM-REDIAL.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2024-llm">
<titleInfo>
<title>LLM-REDIAL: A Large-Scale Dataset for Conversational Recommender Systems Created from User Behaviors with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tingting</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenxin</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingzhi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqi</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Congying</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuyu</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The large-scale conversational recommendation dataset is pivotal for the development of conversational recommender systems (CRS). Most existing CRS datasets suffers from the problems of data inextensibility and semantic inconsistency. To tackle these limitations and establish a benchmark in the conversational recommendation scenario, in this paper, we introduce the LLM-REDIAL dataset to facilitate the research in CRS. LLM-REDIAL is constructed by leveraging large language models (LLMs) to generate the high-quality dialogues. To provide the LLMs with detailed guidance, we integrate historical user behavior data with dialogue templates that are carefully designed through the combination of multiple pre-defined goals. LLM-REDIAL has two main advantages. First, it is the largest multi-domain CRS dataset which consists of 47.6k multi-turn dialogues with 482.6k utterances across 4 domains. Second, dialogue semantics and the users’ historical interaction information is highly consistent. Human evaluation are conducted to verify the quality of LLM-REDIAL. In addition, we evaluate the usability of advanced LLM-based models on LLM-REDIAL.</abstract>
<identifier type="citekey">liang-etal-2024-llm</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.529</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.529</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>8926</start>
<end>8939</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM-REDIAL: A Large-Scale Dataset for Conversational Recommender Systems Created from User Behaviors with LLMs
%A Liang, Tingting
%A Jin, Chenxin
%A Wang, Lingzhi
%A Fan, Wenqi
%A Xia, Congying
%A Chen, Kai
%A Yin, Yuyu
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F liang-etal-2024-llm
%X The large-scale conversational recommendation dataset is pivotal for the development of conversational recommender systems (CRS). Most existing CRS datasets suffers from the problems of data inextensibility and semantic inconsistency. To tackle these limitations and establish a benchmark in the conversational recommendation scenario, in this paper, we introduce the LLM-REDIAL dataset to facilitate the research in CRS. LLM-REDIAL is constructed by leveraging large language models (LLMs) to generate the high-quality dialogues. To provide the LLMs with detailed guidance, we integrate historical user behavior data with dialogue templates that are carefully designed through the combination of multiple pre-defined goals. LLM-REDIAL has two main advantages. First, it is the largest multi-domain CRS dataset which consists of 47.6k multi-turn dialogues with 482.6k utterances across 4 domains. Second, dialogue semantics and the users’ historical interaction information is highly consistent. Human evaluation are conducted to verify the quality of LLM-REDIAL. In addition, we evaluate the usability of advanced LLM-based models on LLM-REDIAL.
%R 10.18653/v1/2024.findings-acl.529
%U https://aclanthology.org/2024.findings-acl.529
%U https://doi.org/10.18653/v1/2024.findings-acl.529
%P 8926-8939
Markdown (Informal)
[LLM-REDIAL: A Large-Scale Dataset for Conversational Recommender Systems Created from User Behaviors with LLMs](https://aclanthology.org/2024.findings-acl.529) (Liang et al., Findings 2024)
ACL