@inproceedings{park-etal-2024-predict,
title = "{PREDICT}: Multi-Agent-based Debate Simulation for Generalized Hate Speech Detection",
author = "Park, Someen and
Kim, Jaehoon and
Jin, Seungwan and
Park, Sohyun and
Han, Kyungsik",
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.1166",
pages = "20963--20987",
abstract = "While a few public benchmarks have been proposed for training hate speech detection models, the differences in labeling criteria between these benchmarks pose challenges for generalized learning, limiting the applicability of the models. Previous research has presented methods to generalize models through data integration or augmentation, but overcoming the differences in labeling criteria between datasets remains a limitation. To address these challenges, we propose PREDICT, a novel framework that uses the notion of multi-agent for hate speech detection. PREDICT consists of two phases: (1) PRE (Perspective-based REasoning): Multiple agents are created based on the induced labeling criteria of given datasets, and each agent generates stances and reasons; (2) DICT (Debate using InCongruenT references): Agents representing hate and non-hate stances conduct the debate, and a judge agent classifies hate or non-hate and provides a balanced reason. Experiments on five representative public benchmarks show that PREDICT achieves superior cross-evaluation performance compared to methods that focus on specific labeling criteria or majority voting methods. Furthermore, we validate that PREDICT effectively mediates differences between agents{'} opinions and appropriately incorporates minority opinions to reach a consensus. Our code is available at https://github.com/Hanyang-HCC-Lab/PREDICT",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2024-predict">
<titleInfo>
<title>PREDICT: Multi-Agent-based Debate Simulation for Generalized Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Someen</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaehoon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungwan</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sohyun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyungsik</namePart>
<namePart type="family">Han</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>While a few public benchmarks have been proposed for training hate speech detection models, the differences in labeling criteria between these benchmarks pose challenges for generalized learning, limiting the applicability of the models. Previous research has presented methods to generalize models through data integration or augmentation, but overcoming the differences in labeling criteria between datasets remains a limitation. To address these challenges, we propose PREDICT, a novel framework that uses the notion of multi-agent for hate speech detection. PREDICT consists of two phases: (1) PRE (Perspective-based REasoning): Multiple agents are created based on the induced labeling criteria of given datasets, and each agent generates stances and reasons; (2) DICT (Debate using InCongruenT references): Agents representing hate and non-hate stances conduct the debate, and a judge agent classifies hate or non-hate and provides a balanced reason. Experiments on five representative public benchmarks show that PREDICT achieves superior cross-evaluation performance compared to methods that focus on specific labeling criteria or majority voting methods. Furthermore, we validate that PREDICT effectively mediates differences between agents’ opinions and appropriately incorporates minority opinions to reach a consensus. Our code is available at https://github.com/Hanyang-HCC-Lab/PREDICT</abstract>
<identifier type="citekey">park-etal-2024-predict</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.1166</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>20963</start>
<end>20987</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PREDICT: Multi-Agent-based Debate Simulation for Generalized Hate Speech Detection
%A Park, Someen
%A Kim, Jaehoon
%A Jin, Seungwan
%A Park, Sohyun
%A Han, Kyungsik
%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 park-etal-2024-predict
%X While a few public benchmarks have been proposed for training hate speech detection models, the differences in labeling criteria between these benchmarks pose challenges for generalized learning, limiting the applicability of the models. Previous research has presented methods to generalize models through data integration or augmentation, but overcoming the differences in labeling criteria between datasets remains a limitation. To address these challenges, we propose PREDICT, a novel framework that uses the notion of multi-agent for hate speech detection. PREDICT consists of two phases: (1) PRE (Perspective-based REasoning): Multiple agents are created based on the induced labeling criteria of given datasets, and each agent generates stances and reasons; (2) DICT (Debate using InCongruenT references): Agents representing hate and non-hate stances conduct the debate, and a judge agent classifies hate or non-hate and provides a balanced reason. Experiments on five representative public benchmarks show that PREDICT achieves superior cross-evaluation performance compared to methods that focus on specific labeling criteria or majority voting methods. Furthermore, we validate that PREDICT effectively mediates differences between agents’ opinions and appropriately incorporates minority opinions to reach a consensus. Our code is available at https://github.com/Hanyang-HCC-Lab/PREDICT
%U https://aclanthology.org/2024.emnlp-main.1166
%P 20963-20987
Markdown (Informal)
[PREDICT: Multi-Agent-based Debate Simulation for Generalized Hate Speech Detection](https://aclanthology.org/2024.emnlp-main.1166) (Park et al., EMNLP 2024)
ACL