GPT detectors are biased against non-native English writers

GPT detectors frequently misclassify non-native English writing as AI generated, raising concerns about fairness and robustness. Addressing the biases in these detectors is crucial to prevent the marginalization of non-native English speakers in evaluative and educational settings and to create a mo...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Patterns (New York, N.Y.) Ročník 4; číslo 7; s. 100779
Hlavní autoři:	Liang, Weixin, Yuksekgonul, Mert, Mao, Yining, Wu, Eric, Zou, James
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States Elsevier Inc 14.07.2023 Elsevier
Témata:	Opinion
ISSN:	2666-3899, 2666-3899
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	GPT detectors frequently misclassify non-native English writing as AI generated, raising concerns about fairness and robustness. Addressing the biases in these detectors is crucial to prevent the marginalization of non-native English speakers in evaluative and educational settings and to create a more equitable digital landscape.
Bibliografie:	content type line 23 SourceType-Scholarly Journals-1 ObjectType-News-1 These authors contributed equally
ISSN:	2666-3899 2666-3899
DOI:	10.1016/j.patter.2023.100779