@inproceedings{uchendu-etal-2021-turingbench-benchmark,
title = "{TURINGBENCH}: A Benchmark Environment for {T}uring Test in the Age of Neural Text Generation",
author = "Uchendu, Adaku and
Ma, Zeyu and
Le, Thai and
Zhang, Rui and
Lee, Dongwon",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.172",
doi = "10.18653/v1/2021.findings-emnlp.172",
pages = "2001--2016",
abstract = "Recent progress in generative language models has enabled machines to generate astonishingly realistic texts. While there are many legitimate applications of such models, there is also a rising need to distinguish machine-generated texts from human-written ones (e.g., fake news detection). However, to our best knowledge, there is currently no benchmark environment with datasets and tasks to systematically study the so-called {''}Turing Test{''} problem for neural text generation methods. In this work, we present the TURINGBENCH benchmark environment, which is comprised of (1) a dataset with 200K human- or machine-generated samples across 20 labels Human, GPT-1, GPT-2{\_}small, GPT-2{\_}medium, GPT-2{\_}large,GPT-2{\_}xl, GPT-2{\_}PyTorch, GPT-3, GROVER{\_}base, GROVER{\_}large, GROVER{\_}mega, CTRL, XLM, XLNET{\_}base, XLNET{\_}large, FAIR{\_}wmt19, FAIR{\_}wmt20, TRANSFORMER{\_}XL, PPLM{\_}distil, PPLM{\_}gpt2, (2) two benchmark tasks{--}i.e., Turing Test (TT) and Authorship Attribution (AA), and (3) a website with leaderboards. Our preliminary experimental results using TURINGBENCH show that GPT-3 and FAIR{\_}wmt20 are the current winners, among all language models tested, in generating the most human-like indistinguishable texts with the lowest F1 score by five state-of-the-art TT detection models. The TURINGBENCH is available at: \url{https://turingbench.ist.psu.edu/}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uchendu-etal-2021-turingbench-benchmark">
<titleInfo>
<title>TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adaku</namePart>
<namePart type="family">Uchendu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeyu</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thai</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongwon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent progress in generative language models has enabled machines to generate astonishingly realistic texts. While there are many legitimate applications of such models, there is also a rising need to distinguish machine-generated texts from human-written ones (e.g., fake news detection). However, to our best knowledge, there is currently no benchmark environment with datasets and tasks to systematically study the so-called ”Turing Test” problem for neural text generation methods. In this work, we present the TURINGBENCH benchmark environment, which is comprised of (1) a dataset with 200K human- or machine-generated samples across 20 labels Human, GPT-1, GPT-2_small, GPT-2_medium, GPT-2_large,GPT-2_xl, GPT-2_PyTorch, GPT-3, GROVER_base, GROVER_large, GROVER_mega, CTRL, XLM, XLNET_base, XLNET_large, FAIR_wmt19, FAIR_wmt20, TRANSFORMER_XL, PPLM_distil, PPLM_gpt2, (2) two benchmark tasks–i.e., Turing Test (TT) and Authorship Attribution (AA), and (3) a website with leaderboards. Our preliminary experimental results using TURINGBENCH show that GPT-3 and FAIR_wmt20 are the current winners, among all language models tested, in generating the most human-like indistinguishable texts with the lowest F1 score by five state-of-the-art TT detection models. The TURINGBENCH is available at: https://turingbench.ist.psu.edu/</abstract>
<identifier type="citekey">uchendu-etal-2021-turingbench-benchmark</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.172</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.172</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2001</start>
<end>2016</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation
%A Uchendu, Adaku
%A Ma, Zeyu
%A Le, Thai
%A Zhang, Rui
%A Lee, Dongwon
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F uchendu-etal-2021-turingbench-benchmark
%X Recent progress in generative language models has enabled machines to generate astonishingly realistic texts. While there are many legitimate applications of such models, there is also a rising need to distinguish machine-generated texts from human-written ones (e.g., fake news detection). However, to our best knowledge, there is currently no benchmark environment with datasets and tasks to systematically study the so-called ”Turing Test” problem for neural text generation methods. In this work, we present the TURINGBENCH benchmark environment, which is comprised of (1) a dataset with 200K human- or machine-generated samples across 20 labels Human, GPT-1, GPT-2_small, GPT-2_medium, GPT-2_large,GPT-2_xl, GPT-2_PyTorch, GPT-3, GROVER_base, GROVER_large, GROVER_mega, CTRL, XLM, XLNET_base, XLNET_large, FAIR_wmt19, FAIR_wmt20, TRANSFORMER_XL, PPLM_distil, PPLM_gpt2, (2) two benchmark tasks–i.e., Turing Test (TT) and Authorship Attribution (AA), and (3) a website with leaderboards. Our preliminary experimental results using TURINGBENCH show that GPT-3 and FAIR_wmt20 are the current winners, among all language models tested, in generating the most human-like indistinguishable texts with the lowest F1 score by five state-of-the-art TT detection models. The TURINGBENCH is available at: https://turingbench.ist.psu.edu/
%R 10.18653/v1/2021.findings-emnlp.172
%U https://aclanthology.org/2021.findings-emnlp.172
%U https://doi.org/10.18653/v1/2021.findings-emnlp.172
%P 2001-2016
Markdown (Informal)
[TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://aclanthology.org/2021.findings-emnlp.172) (Uchendu et al., Findings 2021)
ACL