@inproceedings{gehrmann-etal-2019-gltr,
title = "{GLTR}: Statistical Detection and Visualization of Generated Text",
author = "Gehrmann, Sebastian and
Strobelt, Hendrik and
Rush, Alexander",
editor = "Costa-juss{\`a}, Marta R. and
Alfonseca, Enrique",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-3019",
doi = "10.18653/v1/P19-3019",
pages = "111--116",
abstract = "The rapid improvement of language models has raised the specter of abuse of text generation systems. This progress motivates the development of simple methods for detecting generated text that can be used by non-experts. In this work, we introduce GLTR, a tool to support humans in detecting whether a text was generated by a model. GLTR applies a suite of baseline statistical methods that can detect generation artifacts across multiple sampling schemes. In a human-subjects study, we show that the annotation scheme provided by GLTR improves the human detection-rate of fake text from 54{\%} to 72{\%} without any prior training. GLTR is open-source and publicly deployed, and has already been widely used to detect generated outputs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gehrmann-etal-2019-gltr">
<titleInfo>
<title>GLTR: Statistical Detection and Visualization of Generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hendrik</namePart>
<namePart type="family">Strobelt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Rush</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="family">Alfonseca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The rapid improvement of language models has raised the specter of abuse of text generation systems. This progress motivates the development of simple methods for detecting generated text that can be used by non-experts. In this work, we introduce GLTR, a tool to support humans in detecting whether a text was generated by a model. GLTR applies a suite of baseline statistical methods that can detect generation artifacts across multiple sampling schemes. In a human-subjects study, we show that the annotation scheme provided by GLTR improves the human detection-rate of fake text from 54% to 72% without any prior training. GLTR is open-source and publicly deployed, and has already been widely used to detect generated outputs.</abstract>
<identifier type="citekey">gehrmann-etal-2019-gltr</identifier>
<identifier type="doi">10.18653/v1/P19-3019</identifier>
<location>
<url>https://aclanthology.org/P19-3019</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>111</start>
<end>116</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GLTR: Statistical Detection and Visualization of Generated Text
%A Gehrmann, Sebastian
%A Strobelt, Hendrik
%A Rush, Alexander
%Y Costa-jussà, Marta R.
%Y Alfonseca, Enrique
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F gehrmann-etal-2019-gltr
%X The rapid improvement of language models has raised the specter of abuse of text generation systems. This progress motivates the development of simple methods for detecting generated text that can be used by non-experts. In this work, we introduce GLTR, a tool to support humans in detecting whether a text was generated by a model. GLTR applies a suite of baseline statistical methods that can detect generation artifacts across multiple sampling schemes. In a human-subjects study, we show that the annotation scheme provided by GLTR improves the human detection-rate of fake text from 54% to 72% without any prior training. GLTR is open-source and publicly deployed, and has already been widely used to detect generated outputs.
%R 10.18653/v1/P19-3019
%U https://aclanthology.org/P19-3019
%U https://doi.org/10.18653/v1/P19-3019
%P 111-116
Markdown (Informal)
[GLTR: Statistical Detection and Visualization of Generated Text](https://aclanthology.org/P19-3019) (Gehrmann et al., ACL 2019)
ACL
- Sebastian Gehrmann, Hendrik Strobelt, and Alexander Rush. 2019. GLTR: Statistical Detection and Visualization of Generated Text. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 111–116, Florence, Italy. Association for Computational Linguistics.