@inproceedings{ozturk-etal-2025-make,
title = "Make Satire Boring Again: Reducing Stylistic Bias of Satirical Corpus by Utilizing Generative {LLM}s",
author = "Ozturk, Asli Umay and
Cekinel, Recep Firat and
Karagoz, Pinar",
editor = "Sharoff, Serge and
Terryn, Ayla Rigouts and
Zweigenbaum, Pierre and
Rapp, Reinhard",
booktitle = "Proceedings of the 18th Workshop on Building and Using Comparable Corpora (BUCC)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bucc-1.4/",
pages = "19--35",
abstract = "Satire detection is essential for accurately extracting opinions from textual data and combating misinformation online. However, the lack of diverse corpora for satire leads to the problem of stylistic bias which impacts the models' detection performances. This study proposes a debiasing approach for satire detection, focusing on reducing biases in training data by utilizing generative large language models. The approach is evaluated in both cross-domain (irony detection) and cross-lingual (English) settings. Results show that the debiasing method enhances the robustness and generalizability of the models for satire and irony detection tasks in Turkish and English. However, its impact on causal language models, such as Llama-3.1, is limited. Additionally, this work curates and presents the Turkish Satirical News Dataset with detailed human annotations, with case studies on classification, debiasing, and explainability."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ozturk-etal-2025-make">
<titleInfo>
<title>Make Satire Boring Again: Reducing Stylistic Bias of Satirical Corpus by Utilizing Generative LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="given">Umay</namePart>
<namePart type="family">Ozturk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Recep</namePart>
<namePart type="given">Firat</namePart>
<namePart type="family">Cekinel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pinar</namePart>
<namePart type="family">Karagoz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Workshop on Building and Using Comparable Corpora (BUCC)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayla</namePart>
<namePart type="given">Rigouts</namePart>
<namePart type="family">Terryn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reinhard</namePart>
<namePart type="family">Rapp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Satire detection is essential for accurately extracting opinions from textual data and combating misinformation online. However, the lack of diverse corpora for satire leads to the problem of stylistic bias which impacts the models’ detection performances. This study proposes a debiasing approach for satire detection, focusing on reducing biases in training data by utilizing generative large language models. The approach is evaluated in both cross-domain (irony detection) and cross-lingual (English) settings. Results show that the debiasing method enhances the robustness and generalizability of the models for satire and irony detection tasks in Turkish and English. However, its impact on causal language models, such as Llama-3.1, is limited. Additionally, this work curates and presents the Turkish Satirical News Dataset with detailed human annotations, with case studies on classification, debiasing, and explainability.</abstract>
<identifier type="citekey">ozturk-etal-2025-make</identifier>
<location>
<url>https://aclanthology.org/2025.bucc-1.4/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>19</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Make Satire Boring Again: Reducing Stylistic Bias of Satirical Corpus by Utilizing Generative LLMs
%A Ozturk, Asli Umay
%A Cekinel, Recep Firat
%A Karagoz, Pinar
%Y Sharoff, Serge
%Y Terryn, Ayla Rigouts
%Y Zweigenbaum, Pierre
%Y Rapp, Reinhard
%S Proceedings of the 18th Workshop on Building and Using Comparable Corpora (BUCC)
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F ozturk-etal-2025-make
%X Satire detection is essential for accurately extracting opinions from textual data and combating misinformation online. However, the lack of diverse corpora for satire leads to the problem of stylistic bias which impacts the models’ detection performances. This study proposes a debiasing approach for satire detection, focusing on reducing biases in training data by utilizing generative large language models. The approach is evaluated in both cross-domain (irony detection) and cross-lingual (English) settings. Results show that the debiasing method enhances the robustness and generalizability of the models for satire and irony detection tasks in Turkish and English. However, its impact on causal language models, such as Llama-3.1, is limited. Additionally, this work curates and presents the Turkish Satirical News Dataset with detailed human annotations, with case studies on classification, debiasing, and explainability.
%U https://aclanthology.org/2025.bucc-1.4/
%P 19-35
Markdown (Informal)
[Make Satire Boring Again: Reducing Stylistic Bias of Satirical Corpus by Utilizing Generative LLMs](https://aclanthology.org/2025.bucc-1.4/) (Ozturk et al., BUCC 2025)
ACL