@inproceedings{brooks-etal-2024-rise,
title = "The Rise of {AI}-Generated Content in {W}ikipedia",
author = "Brooks, Creston and
Eggert, Samuel and
Peskoff, Denis",
editor = "Lucie-Aim{\'e}e, Lucie and
Fan, Angela and
Gwadabe, Tajuddeen and
Johnson, Isaac and
Petroni, Fabio and
van Strien, Daniel",
booktitle = "Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wikinlp-1.12",
pages = "67--79",
abstract = "The rise of AI-generated content in popular information sources raises significant concerns about accountability, accuracy, and bias amplification. Beyond directly impacting consumers, the widespread presence of this content poses questions for the long-term viability of training language models on vast internet sweeps. We use GPTZero, a proprietary AI detector, and Binoculars, an open-source alternative, to establish lower bounds on the presence of AI-generated content in recently created Wikipedia pages. Both detectors reveal a marked increase in AI-generated content in recent pages compared to those from before the release of GPT-3.5. With thresholds calibrated to achieve a 1{\%} false positive rate on pre-GPT-3.5 articles, detectors flag over 5{\%} of newly created English Wikipedia articles as AI-generated, with lower percentages for German, French, and Italian articles. Flagged Wikipedia articles are typically of lower quality and are often self-promotional or partial towards a specific viewpoint on controversial topics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brooks-etal-2024-rise">
<titleInfo>
<title>The Rise of AI-Generated Content in Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Creston</namePart>
<namePart type="family">Brooks</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Eggert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">Peskoff</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 First Workshop on Advancing Natural Language Processing for Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Lucie-Aimée</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tajuddeen</namePart>
<namePart type="family">Gwadabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaac</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Petroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">van Strien</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 rise of AI-generated content in popular information sources raises significant concerns about accountability, accuracy, and bias amplification. Beyond directly impacting consumers, the widespread presence of this content poses questions for the long-term viability of training language models on vast internet sweeps. We use GPTZero, a proprietary AI detector, and Binoculars, an open-source alternative, to establish lower bounds on the presence of AI-generated content in recently created Wikipedia pages. Both detectors reveal a marked increase in AI-generated content in recent pages compared to those from before the release of GPT-3.5. With thresholds calibrated to achieve a 1% false positive rate on pre-GPT-3.5 articles, detectors flag over 5% of newly created English Wikipedia articles as AI-generated, with lower percentages for German, French, and Italian articles. Flagged Wikipedia articles are typically of lower quality and are often self-promotional or partial towards a specific viewpoint on controversial topics.</abstract>
<identifier type="citekey">brooks-etal-2024-rise</identifier>
<location>
<url>https://aclanthology.org/2024.wikinlp-1.12</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>67</start>
<end>79</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Rise of AI-Generated Content in Wikipedia
%A Brooks, Creston
%A Eggert, Samuel
%A Peskoff, Denis
%Y Lucie-Aimée, Lucie
%Y Fan, Angela
%Y Gwadabe, Tajuddeen
%Y Johnson, Isaac
%Y Petroni, Fabio
%Y van Strien, Daniel
%S Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F brooks-etal-2024-rise
%X The rise of AI-generated content in popular information sources raises significant concerns about accountability, accuracy, and bias amplification. Beyond directly impacting consumers, the widespread presence of this content poses questions for the long-term viability of training language models on vast internet sweeps. We use GPTZero, a proprietary AI detector, and Binoculars, an open-source alternative, to establish lower bounds on the presence of AI-generated content in recently created Wikipedia pages. Both detectors reveal a marked increase in AI-generated content in recent pages compared to those from before the release of GPT-3.5. With thresholds calibrated to achieve a 1% false positive rate on pre-GPT-3.5 articles, detectors flag over 5% of newly created English Wikipedia articles as AI-generated, with lower percentages for German, French, and Italian articles. Flagged Wikipedia articles are typically of lower quality and are often self-promotional or partial towards a specific viewpoint on controversial topics.
%U https://aclanthology.org/2024.wikinlp-1.12
%P 67-79
Markdown (Informal)
[The Rise of AI-Generated Content in Wikipedia](https://aclanthology.org/2024.wikinlp-1.12) (Brooks et al., WikiNLP 2024)
ACL
- Creston Brooks, Samuel Eggert, and Denis Peskoff. 2024. The Rise of AI-Generated Content in Wikipedia. In Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia, pages 67–79, Miami, Florida, USA. Association for Computational Linguistics.