@inproceedings{uyuk-etal-2024-crafting,
title = "Crafting Tomorrow{'}s Headlines: Neural News Generation and Detection in {E}nglish, {T}urkish, {H}ungarian, and {P}ersian",
author = {{\"U}y{\"u}k, Cem and
Rov{\'o}, Danica and
Shaghayeghkolli, Shaghayeghkolli and
Varol, Rabia and
Groh, Georg and
Dementieva, Daryna},
editor = "Dementieva, Daryna and
Ignat, Oana and
Jin, Zhijing and
Mihalcea, Rada and
Piatti, Giorgio and
Tetreault, Joel and
Wilson, Steven and
Zhao, Jieyu",
booktitle = "Proceedings of the Third Workshop on NLP for Positive Impact",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nlp4pi-1.25",
pages = "271--307",
abstract = "In the era dominated by information overload and its facilitation with Large Language Models (LLMs), the prevalence of misinformation poses a significant threat to public discourse and societal well-being. A critical concern at present involves the identification of machine-generated news. In this work, we take a significant step by introducing a benchmark dataset designed for neural news detection in four languages: English, Turkish, Hungarian, and Persian. The dataset incorporates outputs from multiple multilingual generators (in both, zero-shot and fine-tuned setups) such as BloomZ, LLaMa-2, Mistral, Mixtral, and GPT-4. Next, we experiment with a variety of classifiers, ranging from those based on linguistic features to advanced Transformer-based models and LLMs prompting. We present the detection results aiming to delve into the interpretablity and robustness of machine-generated texts detectors across all target languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uyuk-etal-2024-crafting">
<titleInfo>
<title>Crafting Tomorrow’s Headlines: Neural News Generation and Detection in English, Turkish, Hungarian, and Persian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cem</namePart>
<namePart type="family">Üyük</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danica</namePart>
<namePart type="family">Rovó</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaghayeghkolli</namePart>
<namePart type="family">Shaghayeghkolli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rabia</namePart>
<namePart type="family">Varol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Groh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daryna</namePart>
<namePart type="family">Dementieva</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 Third Workshop on NLP for Positive Impact</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daryna</namePart>
<namePart type="family">Dementieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Ignat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhijing</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giorgio</namePart>
<namePart type="family">Piatti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</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>In the era dominated by information overload and its facilitation with Large Language Models (LLMs), the prevalence of misinformation poses a significant threat to public discourse and societal well-being. A critical concern at present involves the identification of machine-generated news. In this work, we take a significant step by introducing a benchmark dataset designed for neural news detection in four languages: English, Turkish, Hungarian, and Persian. The dataset incorporates outputs from multiple multilingual generators (in both, zero-shot and fine-tuned setups) such as BloomZ, LLaMa-2, Mistral, Mixtral, and GPT-4. Next, we experiment with a variety of classifiers, ranging from those based on linguistic features to advanced Transformer-based models and LLMs prompting. We present the detection results aiming to delve into the interpretablity and robustness of machine-generated texts detectors across all target languages.</abstract>
<identifier type="citekey">uyuk-etal-2024-crafting</identifier>
<location>
<url>https://aclanthology.org/2024.nlp4pi-1.25</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>271</start>
<end>307</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Crafting Tomorrow’s Headlines: Neural News Generation and Detection in English, Turkish, Hungarian, and Persian
%A Üyük, Cem
%A Rovó, Danica
%A Shaghayeghkolli, Shaghayeghkolli
%A Varol, Rabia
%A Groh, Georg
%A Dementieva, Daryna
%Y Dementieva, Daryna
%Y Ignat, Oana
%Y Jin, Zhijing
%Y Mihalcea, Rada
%Y Piatti, Giorgio
%Y Tetreault, Joel
%Y Wilson, Steven
%Y Zhao, Jieyu
%S Proceedings of the Third Workshop on NLP for Positive Impact
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F uyuk-etal-2024-crafting
%X In the era dominated by information overload and its facilitation with Large Language Models (LLMs), the prevalence of misinformation poses a significant threat to public discourse and societal well-being. A critical concern at present involves the identification of machine-generated news. In this work, we take a significant step by introducing a benchmark dataset designed for neural news detection in four languages: English, Turkish, Hungarian, and Persian. The dataset incorporates outputs from multiple multilingual generators (in both, zero-shot and fine-tuned setups) such as BloomZ, LLaMa-2, Mistral, Mixtral, and GPT-4. Next, we experiment with a variety of classifiers, ranging from those based on linguistic features to advanced Transformer-based models and LLMs prompting. We present the detection results aiming to delve into the interpretablity and robustness of machine-generated texts detectors across all target languages.
%U https://aclanthology.org/2024.nlp4pi-1.25
%P 271-307
Markdown (Informal)
[Crafting Tomorrow’s Headlines: Neural News Generation and Detection in English, Turkish, Hungarian, and Persian](https://aclanthology.org/2024.nlp4pi-1.25) (Üyük et al., NLP4PI 2024)
ACL
- Cem Üyük, Danica Rovó, Shaghayeghkolli Shaghayeghkolli, Rabia Varol, Georg Groh, and Daryna Dementieva. 2024. Crafting Tomorrow’s Headlines: Neural News Generation and Detection in English, Turkish, Hungarian, and Persian. In Proceedings of the Third Workshop on NLP for Positive Impact, pages 271–307, Miami, Florida, USA. Association for Computational Linguistics.