@inproceedings{shin-etal-2024-learning,
title = "Learning to Adapt Large Language Models to One-Shot In-Context Intent Classification on Unseen Domains",
author = "Shin, Joongbo and
Ahn, Youbin and
Won, Seungpil and
Choi, Stanley Jungkyu",
editor = "Kumar, Sachin and
Balachandran, Vidhisha and
Park, Chan Young and
Shi, Weijia and
Hayati, Shirley Anugrah and
Tsvetkov, Yulia and
Smith, Noah and
Hajishirzi, Hannaneh and
Kang, Dongyeop and
Jurgens, David",
booktitle = "Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.customnlp4u-1.15",
pages = "182--197",
abstract = "In this paper, we explore one-shot in-context intent classification using large language models (LLMs) with the goal of minimizing the effort required to adapt models to unseen domains. To enhance the one-shot in-context learning capabilities of LLMs, we employ in-context tuning, leveraging its cross-domain transferability to unseen domains.To this end, we introduce the IC-collection, a compilation of open-source intent classification datasets from diverse domains, which are meticulously divided into held-in and held-out datasets.Our experiments demonstrate the effectiveness of the proposed method, showing that our model, with only 7B parameters, not only outperforms GPT-4 on intent classification but also achieves state-of-the-art in unseen domains with only one-shot demonstrations.Both our benchmark and model will be made publicly available to advance research in the chatbot systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shin-etal-2024-learning">
<titleInfo>
<title>Learning to Adapt Large Language Models to One-Shot In-Context Intent Classification on Unseen Domains</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joongbo</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youbin</namePart>
<namePart type="family">Ahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungpil</namePart>
<namePart type="family">Won</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stanley</namePart>
<namePart type="given">Jungkyu</namePart>
<namePart type="family">Choi</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 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sachin</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vidhisha</namePart>
<namePart type="family">Balachandran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chan</namePart>
<namePart type="given">Young</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijia</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shirley</namePart>
<namePart type="given">Anugrah</namePart>
<namePart type="family">Hayati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Tsvetkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannaneh</namePart>
<namePart type="family">Hajishirzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongyeop</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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>In this paper, we explore one-shot in-context intent classification using large language models (LLMs) with the goal of minimizing the effort required to adapt models to unseen domains. To enhance the one-shot in-context learning capabilities of LLMs, we employ in-context tuning, leveraging its cross-domain transferability to unseen domains.To this end, we introduce the IC-collection, a compilation of open-source intent classification datasets from diverse domains, which are meticulously divided into held-in and held-out datasets.Our experiments demonstrate the effectiveness of the proposed method, showing that our model, with only 7B parameters, not only outperforms GPT-4 on intent classification but also achieves state-of-the-art in unseen domains with only one-shot demonstrations.Both our benchmark and model will be made publicly available to advance research in the chatbot systems.</abstract>
<identifier type="citekey">shin-etal-2024-learning</identifier>
<location>
<url>https://aclanthology.org/2024.customnlp4u-1.15</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>182</start>
<end>197</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Adapt Large Language Models to One-Shot In-Context Intent Classification on Unseen Domains
%A Shin, Joongbo
%A Ahn, Youbin
%A Won, Seungpil
%A Choi, Stanley Jungkyu
%Y Kumar, Sachin
%Y Balachandran, Vidhisha
%Y Park, Chan Young
%Y Shi, Weijia
%Y Hayati, Shirley Anugrah
%Y Tsvetkov, Yulia
%Y Smith, Noah
%Y Hajishirzi, Hannaneh
%Y Kang, Dongyeop
%Y Jurgens, David
%S Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F shin-etal-2024-learning
%X In this paper, we explore one-shot in-context intent classification using large language models (LLMs) with the goal of minimizing the effort required to adapt models to unseen domains. To enhance the one-shot in-context learning capabilities of LLMs, we employ in-context tuning, leveraging its cross-domain transferability to unseen domains.To this end, we introduce the IC-collection, a compilation of open-source intent classification datasets from diverse domains, which are meticulously divided into held-in and held-out datasets.Our experiments demonstrate the effectiveness of the proposed method, showing that our model, with only 7B parameters, not only outperforms GPT-4 on intent classification but also achieves state-of-the-art in unseen domains with only one-shot demonstrations.Both our benchmark and model will be made publicly available to advance research in the chatbot systems.
%U https://aclanthology.org/2024.customnlp4u-1.15
%P 182-197
Markdown (Informal)
[Learning to Adapt Large Language Models to One-Shot In-Context Intent Classification on Unseen Domains](https://aclanthology.org/2024.customnlp4u-1.15) (Shin et al., CustomNLP4U 2024)
ACL
- Joongbo Shin, Youbin Ahn, Seungpil Won, and Stanley Jungkyu Choi. 2024. Learning to Adapt Large Language Models to One-Shot In-Context Intent Classification on Unseen Domains. In Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U), pages 182–197, Miami, Florida, USA. Association for Computational Linguistics.