@inproceedings{zhang-etal-2024-llm-driven,
title = "{LLM}-Driven Knowledge Injection Advances Zero-Shot and Cross-Target Stance Detection",
author = "Zhang, Zhao and
Li, Yiming and
Zhang, Jin and
Xu, Hui",
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 2: Short Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-short.32/",
doi = "10.18653/v1/2024.naacl-short.32",
pages = "371--378",
abstract = "Stance detection aims at inferring an author`s attitude towards a specific target in a text. Prior methods mainly consider target-related background information for a better understanding of targets while neglecting the accompanying input texts. In this study, we propose to prompt Large Language Models (LLMs) to explicitly extract the relationship between paired text and target as contextual knowledge. We then inject such LLM-driven knowledge into a generation model BART to exploit the rich contexts and semantics. Moreover, to further enhance the decoding capability of BART, a novel prototypical contrastive scheme is designed to align input contents with stance labels. Our experimental results demonstrate the state-of-the-art performance across several publicly available datasets, showcasing effectiveness in both zero-shot and cross-target stance detection scenarios. We publicly release our code to facilitate future research."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-llm-driven">
<titleInfo>
<title>LLM-Driven Knowledge Injection Advances Zero-Shot and Cross-Target Stance Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Xu</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 2: Short 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>Stance detection aims at inferring an author‘s attitude towards a specific target in a text. Prior methods mainly consider target-related background information for a better understanding of targets while neglecting the accompanying input texts. In this study, we propose to prompt Large Language Models (LLMs) to explicitly extract the relationship between paired text and target as contextual knowledge. We then inject such LLM-driven knowledge into a generation model BART to exploit the rich contexts and semantics. Moreover, to further enhance the decoding capability of BART, a novel prototypical contrastive scheme is designed to align input contents with stance labels. Our experimental results demonstrate the state-of-the-art performance across several publicly available datasets, showcasing effectiveness in both zero-shot and cross-target stance detection scenarios. We publicly release our code to facilitate future research.</abstract>
<identifier type="citekey">zhang-etal-2024-llm-driven</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-short.32</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-short.32/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>371</start>
<end>378</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM-Driven Knowledge Injection Advances Zero-Shot and Cross-Target Stance Detection
%A Zhang, Zhao
%A Li, Yiming
%A Zhang, Jin
%A Xu, Hui
%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 2: Short Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F zhang-etal-2024-llm-driven
%X Stance detection aims at inferring an author‘s attitude towards a specific target in a text. Prior methods mainly consider target-related background information for a better understanding of targets while neglecting the accompanying input texts. In this study, we propose to prompt Large Language Models (LLMs) to explicitly extract the relationship between paired text and target as contextual knowledge. We then inject such LLM-driven knowledge into a generation model BART to exploit the rich contexts and semantics. Moreover, to further enhance the decoding capability of BART, a novel prototypical contrastive scheme is designed to align input contents with stance labels. Our experimental results demonstrate the state-of-the-art performance across several publicly available datasets, showcasing effectiveness in both zero-shot and cross-target stance detection scenarios. We publicly release our code to facilitate future research.
%R 10.18653/v1/2024.naacl-short.32
%U https://aclanthology.org/2024.naacl-short.32/
%U https://doi.org/10.18653/v1/2024.naacl-short.32
%P 371-378
Markdown (Informal)
[LLM-Driven Knowledge Injection Advances Zero-Shot and Cross-Target Stance Detection](https://aclanthology.org/2024.naacl-short.32/) (Zhang et al., NAACL 2024)
ACL