GPT检测器对非英语母语的写作者存在偏见。
GPT detectors are biased against non-native English writers.
作者信息
Liang Weixin, Yuksekgonul Mert, Mao Yining, Wu Eric, Zou James
机构信息
Department of Computer Science, Stanford University, Stanford, CA, USA.
Department of Electrical Engineering, Stanford University, Stanford, CA, USA.
出版信息
Patterns (N Y). 2023 Jul 10;4(7):100779. doi: 10.1016/j.patter.2023.100779. eCollection 2023 Jul 14.
Abstract
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.
摘要
GPT检测工具经常将非英语母语者的写作错误地归类为人工智能生成的内容，这引发了人们对公平性和稳健性的担忧。解决这些检测工具中的偏见对于防止非英语母语者在评估和教育环境中被边缘化，并创造一个更加公平的数字环境至关重要。
Zotero 插件