@inproceedings{cheng-etal-2024-dialogues,
title = "{``}In-Dialogues We Learn{''}: Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning",
author = "Cheng, Chuanqi and
Tu, Quan and
Wu, Wei and
Shang, Shuo and
Mao, Cunli and
Yu, Zhengtao and
Yan, Rui",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.581",
doi = "10.18653/v1/2024.emnlp-main.581",
pages = "10408--10422",
abstract = "Personalized dialogue systems have gained significant attention in recent years for their ability to generate responses in alignment with different personas. However, most existing approaches rely on pre-defined personal profiles, which are not only time-consuming and labor-intensive to create but also lack flexibility. We propose In-Dialogue Learning (IDL), a fine-tuning framework that enhances the ability of pre-trained large language models to leverage dialogue history to characterize persona for personalized dialogue generation tasks without pre-defined profiles. Our experiments on three datasets demonstrate that IDL brings substantial improvements, with BLEU and ROUGE scores increasing by up to 200{\%} and 247{\%}, respectively. Additionally, the results of human evaluations further validate the efficacy of our proposed method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2024-dialogues">
<titleInfo>
<title>“In-Dialogues We Learn”: Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chuanqi</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cunli</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengtao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Personalized dialogue systems have gained significant attention in recent years for their ability to generate responses in alignment with different personas. However, most existing approaches rely on pre-defined personal profiles, which are not only time-consuming and labor-intensive to create but also lack flexibility. We propose In-Dialogue Learning (IDL), a fine-tuning framework that enhances the ability of pre-trained large language models to leverage dialogue history to characterize persona for personalized dialogue generation tasks without pre-defined profiles. Our experiments on three datasets demonstrate that IDL brings substantial improvements, with BLEU and ROUGE scores increasing by up to 200% and 247%, respectively. Additionally, the results of human evaluations further validate the efficacy of our proposed method.</abstract>
<identifier type="citekey">cheng-etal-2024-dialogues</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.581</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.581</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>10408</start>
<end>10422</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T “In-Dialogues We Learn”: Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning
%A Cheng, Chuanqi
%A Tu, Quan
%A Wu, Wei
%A Shang, Shuo
%A Mao, Cunli
%A Yu, Zhengtao
%A Yan, Rui
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F cheng-etal-2024-dialogues
%X Personalized dialogue systems have gained significant attention in recent years for their ability to generate responses in alignment with different personas. However, most existing approaches rely on pre-defined personal profiles, which are not only time-consuming and labor-intensive to create but also lack flexibility. We propose In-Dialogue Learning (IDL), a fine-tuning framework that enhances the ability of pre-trained large language models to leverage dialogue history to characterize persona for personalized dialogue generation tasks without pre-defined profiles. Our experiments on three datasets demonstrate that IDL brings substantial improvements, with BLEU and ROUGE scores increasing by up to 200% and 247%, respectively. Additionally, the results of human evaluations further validate the efficacy of our proposed method.
%R 10.18653/v1/2024.emnlp-main.581
%U https://aclanthology.org/2024.emnlp-main.581
%U https://doi.org/10.18653/v1/2024.emnlp-main.581
%P 10408-10422
Markdown (Informal)
[“In-Dialogues We Learn”: Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning](https://aclanthology.org/2024.emnlp-main.581) (Cheng et al., EMNLP 2024)
ACL
- Chuanqi Cheng, Quan Tu, Wei Wu, Shuo Shang, Cunli Mao, Zhengtao Yu, and Rui Yan. 2024. “In-Dialogues We Learn”: Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 10408–10422, Miami, Florida, USA. Association for Computational Linguistics.