@inproceedings{liang-etal-2024-synergizing,
title = "Synergizing Large Language Models and Pre-Trained Smaller Models for Conversational Intent Discovery",
author = "Liang, Jinggui and
Liao, Lizi and
Fei, Hao and
Jiang, Jing",
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 and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.840",
pages = "14133--14147",
abstract = "In Conversational Intent Discovery (CID), Small Language Models (SLMs) struggle with overfitting to familiar intents and fail to label newly discovered ones. This issue stems from their limited grasp of semantic nuances and their intrinsically discriminative framework. Therefore, we propose Synergizing Large Language Models (LLMs) with pre-trained SLMs for CID (SynCID). It harnesses the profound semantic comprehension of LLMs alongside the operational agility of SLMs. By utilizing LLMs to refine both utterances and existing intent labels, SynCID significantly enhances the semantic depth, subsequently realigning these enriched descriptors within the SLMs{'} feature space to correct cluster distortion and promote robust learning of representations. A key advantage is its capacity for the early identification of new intents, a critical aspect for deploying conversational agents successfully. Additionally, SynCID leverages the in-context learning strengths of LLMs to generate labels for new intents. Thorough evaluations across a wide array of datasets have demonstrated its superior performance over traditional CID methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2024-synergizing">
<titleInfo>
<title>Synergizing Large Language Models and Pre-Trained Smaller Models for Conversational Intent Discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinggui</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizi</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</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 and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In Conversational Intent Discovery (CID), Small Language Models (SLMs) struggle with overfitting to familiar intents and fail to label newly discovered ones. This issue stems from their limited grasp of semantic nuances and their intrinsically discriminative framework. Therefore, we propose Synergizing Large Language Models (LLMs) with pre-trained SLMs for CID (SynCID). It harnesses the profound semantic comprehension of LLMs alongside the operational agility of SLMs. By utilizing LLMs to refine both utterances and existing intent labels, SynCID significantly enhances the semantic depth, subsequently realigning these enriched descriptors within the SLMs’ feature space to correct cluster distortion and promote robust learning of representations. A key advantage is its capacity for the early identification of new intents, a critical aspect for deploying conversational agents successfully. Additionally, SynCID leverages the in-context learning strengths of LLMs to generate labels for new intents. Thorough evaluations across a wide array of datasets have demonstrated its superior performance over traditional CID methods.</abstract>
<identifier type="citekey">liang-etal-2024-synergizing</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.840</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>14133</start>
<end>14147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Synergizing Large Language Models and Pre-Trained Smaller Models for Conversational Intent Discovery
%A Liang, Jinggui
%A Liao, Lizi
%A Fei, Hao
%A Jiang, Jing
%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 and virtual meeting
%F liang-etal-2024-synergizing
%X In Conversational Intent Discovery (CID), Small Language Models (SLMs) struggle with overfitting to familiar intents and fail to label newly discovered ones. This issue stems from their limited grasp of semantic nuances and their intrinsically discriminative framework. Therefore, we propose Synergizing Large Language Models (LLMs) with pre-trained SLMs for CID (SynCID). It harnesses the profound semantic comprehension of LLMs alongside the operational agility of SLMs. By utilizing LLMs to refine both utterances and existing intent labels, SynCID significantly enhances the semantic depth, subsequently realigning these enriched descriptors within the SLMs’ feature space to correct cluster distortion and promote robust learning of representations. A key advantage is its capacity for the early identification of new intents, a critical aspect for deploying conversational agents successfully. Additionally, SynCID leverages the in-context learning strengths of LLMs to generate labels for new intents. Thorough evaluations across a wide array of datasets have demonstrated its superior performance over traditional CID methods.
%U https://aclanthology.org/2024.findings-acl.840
%P 14133-14147
Markdown (Informal)
[Synergizing Large Language Models and Pre-Trained Smaller Models for Conversational Intent Discovery](https://aclanthology.org/2024.findings-acl.840) (Liang et al., Findings 2024)
ACL