@inproceedings{liang-etal-2024-actively,
title = "Actively Learn from {LLM}s with Uncertainty Propagation for Generalized Category Discovery",
author = "Liang, Jinggui and
Liao, Lizi and
Fei, Hao and
Li, Bobo and
Jiang, Jing",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.434",
doi = "10.18653/v1/2024.naacl-long.434",
pages = "7845--7858",
abstract = "Generalized category discovery faces a key issue: the lack of supervision for new and unseen data categories. Traditional methods typically combine supervised pretraining with self-supervised learning to create models, and then employ clustering for category identification. However, these approaches tend to become overly tailored to known categories, failing to fully resolve the core issue. Hence, we propose to integrate the feedback from LLMs into an active learning paradigm. Specifically, our method innovatively employs uncertainty propagation to select data samples from high-uncertainty regions, which are then labeled using LLMs through a comparison-based prompting scheme. This not only eases the labeling task but also enhances accuracy in identifying new categories. Additionally, a soft feedback propagation mechanism is introduced to minimize the spread of inaccurate feedback. Experiments on various datasets demonstrate our framework{'}s efficacy and generalizability, significantly improving baseline models at a nominal average cost.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2024-actively">
<titleInfo>
<title>Actively Learn from LLMs with Uncertainty Propagation for Generalized Category 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">Bobo</namePart>
<namePart type="family">Li</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>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generalized category discovery faces a key issue: the lack of supervision for new and unseen data categories. Traditional methods typically combine supervised pretraining with self-supervised learning to create models, and then employ clustering for category identification. However, these approaches tend to become overly tailored to known categories, failing to fully resolve the core issue. Hence, we propose to integrate the feedback from LLMs into an active learning paradigm. Specifically, our method innovatively employs uncertainty propagation to select data samples from high-uncertainty regions, which are then labeled using LLMs through a comparison-based prompting scheme. This not only eases the labeling task but also enhances accuracy in identifying new categories. Additionally, a soft feedback propagation mechanism is introduced to minimize the spread of inaccurate feedback. Experiments on various datasets demonstrate our framework’s efficacy and generalizability, significantly improving baseline models at a nominal average cost.</abstract>
<identifier type="citekey">liang-etal-2024-actively</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.434</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.434</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>7845</start>
<end>7858</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Actively Learn from LLMs with Uncertainty Propagation for Generalized Category Discovery
%A Liang, Jinggui
%A Liao, Lizi
%A Fei, Hao
%A Li, Bobo
%A Jiang, Jing
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F liang-etal-2024-actively
%X Generalized category discovery faces a key issue: the lack of supervision for new and unseen data categories. Traditional methods typically combine supervised pretraining with self-supervised learning to create models, and then employ clustering for category identification. However, these approaches tend to become overly tailored to known categories, failing to fully resolve the core issue. Hence, we propose to integrate the feedback from LLMs into an active learning paradigm. Specifically, our method innovatively employs uncertainty propagation to select data samples from high-uncertainty regions, which are then labeled using LLMs through a comparison-based prompting scheme. This not only eases the labeling task but also enhances accuracy in identifying new categories. Additionally, a soft feedback propagation mechanism is introduced to minimize the spread of inaccurate feedback. Experiments on various datasets demonstrate our framework’s efficacy and generalizability, significantly improving baseline models at a nominal average cost.
%R 10.18653/v1/2024.naacl-long.434
%U https://aclanthology.org/2024.naacl-long.434
%U https://doi.org/10.18653/v1/2024.naacl-long.434
%P 7845-7858
Markdown (Informal)
[Actively Learn from LLMs with Uncertainty Propagation for Generalized Category Discovery](https://aclanthology.org/2024.naacl-long.434) (Liang et al., NAACL 2024)
ACL