Problem of cheating with neural networks in language learning

Chi tiết về thư mục
Parent link:Язык. Общество. Образование.— 2023.— С. 141-148
Tác giả chính: Зайда А. В.
Tác giả của công ty: Национальный исследовательский Томский политехнический университет Школа базовой инженерной подготовки Отделение иностранных языков
Tác giả khác: Согуляк Я. А. (727), Аксёнова Н. В. Наталия Валерьевна
Tóm tắt:This study explores the performance of commercially available large language models in common language learning tasks. Structure and working principles of neural networks were considered to hypothesize which tasks would perform better. Experiments were conducted to verify the assumptions. Several variants of task adaptations were compared in tests to discover the most resistant to cheating
Текстовый файл
Ngôn ngữ:Tiếng Anh
Được phát hành: 2023
Loạt:Актуальные векторы исследований и подходы в современной лингвистике
Những chủ đề:
Truy cập trực tuyến:http://earchive.tpu.ru/handle/11683/77924
Định dạng: Điện tử Chương của sách
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=671978
Miêu tả
Tóm tắt:This study explores the performance of commercially available large language models in common language learning tasks. Structure and working principles of neural networks were considered to hypothesize which tasks would perform better. Experiments were conducted to verify the assumptions. Several variants of task adaptations were compared in tests to discover the most resistant to cheating
Текстовый файл