@inproceedings{liu-etal-2024-giving,
title = "Giving Control Back to Models: Enabling Offensive Language Detection Models to Autonomously Identify and Mitigate Biases",
author = "Liu, Jiapeng and
Li, Weijie and
Fan, Xiaochao and
Deng, Wenjun and
Yang, Liang and
Li, Yong and
Diao, Yufeng",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.344",
pages = "5957--5966",
abstract = "The rapid development of social media has led to an increase in online harassment and offensive speech, posing significant challenges for effective content moderation. Existing automated detection models often exhibit a bias towards predicting offensive speech based on specific vocabulary, which not only compromises model fairness but also potentially exacerbates biases against vulnerable and minority groups. Addressing these issues, this paper proposes a bias self-awareness and data self-iteration framework for mitigating model biases. This framework aims to {``}giving control back to models: enabling offensive language detection models to autonomously identify and mitigate biases{''} through bias self-awareness algorithms and self-iterative data augmentation method. Experimental results demonstrate that the proposed framework effectively reduces the false positive rate of models in both in-distribution and out-of-distribution tests, enhances model accuracy and fairness, and shows promising performance improvements in detecting offensive speech on larger-scale datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2024-giving">
<titleInfo>
<title>Giving Control Back to Models: Enabling Offensive Language Detection Models to Autonomously Identify and Mitigate Biases</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiapeng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaochao</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjun</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufeng</namePart>
<namePart type="family">Diao</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>Findings of the Association for Computational Linguistics: EMNLP 2024</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>The rapid development of social media has led to an increase in online harassment and offensive speech, posing significant challenges for effective content moderation. Existing automated detection models often exhibit a bias towards predicting offensive speech based on specific vocabulary, which not only compromises model fairness but also potentially exacerbates biases against vulnerable and minority groups. Addressing these issues, this paper proposes a bias self-awareness and data self-iteration framework for mitigating model biases. This framework aims to “giving control back to models: enabling offensive language detection models to autonomously identify and mitigate biases” through bias self-awareness algorithms and self-iterative data augmentation method. Experimental results demonstrate that the proposed framework effectively reduces the false positive rate of models in both in-distribution and out-of-distribution tests, enhances model accuracy and fairness, and shows promising performance improvements in detecting offensive speech on larger-scale datasets.</abstract>
<identifier type="citekey">liu-etal-2024-giving</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.344</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>5957</start>
<end>5966</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Giving Control Back to Models: Enabling Offensive Language Detection Models to Autonomously Identify and Mitigate Biases
%A Liu, Jiapeng
%A Li, Weijie
%A Fan, Xiaochao
%A Deng, Wenjun
%A Yang, Liang
%A Li, Yong
%A Diao, Yufeng
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F liu-etal-2024-giving
%X The rapid development of social media has led to an increase in online harassment and offensive speech, posing significant challenges for effective content moderation. Existing automated detection models often exhibit a bias towards predicting offensive speech based on specific vocabulary, which not only compromises model fairness but also potentially exacerbates biases against vulnerable and minority groups. Addressing these issues, this paper proposes a bias self-awareness and data self-iteration framework for mitigating model biases. This framework aims to “giving control back to models: enabling offensive language detection models to autonomously identify and mitigate biases” through bias self-awareness algorithms and self-iterative data augmentation method. Experimental results demonstrate that the proposed framework effectively reduces the false positive rate of models in both in-distribution and out-of-distribution tests, enhances model accuracy and fairness, and shows promising performance improvements in detecting offensive speech on larger-scale datasets.
%U https://aclanthology.org/2024.findings-emnlp.344
%P 5957-5966
Markdown (Informal)
[Giving Control Back to Models: Enabling Offensive Language Detection Models to Autonomously Identify and Mitigate Biases](https://aclanthology.org/2024.findings-emnlp.344) (Liu et al., Findings 2024)
ACL
- Jiapeng Liu, Weijie Li, Xiaochao Fan, Wenjun Deng, Liang Yang, Yong Li, and Yufeng Diao. 2024. Giving Control Back to Models: Enabling Offensive Language Detection Models to Autonomously Identify and Mitigate Biases. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 5957–5966, Miami, Florida, USA. Association for Computational Linguistics.