Problem of cheating with neural networks in language learning
| Parent link: | Кобенко, Ю. В. (лингвист ; 1977-). Язык. Общество. Образование: сборник научных трудов IV Международной научно-практической конференции «Лингвистические и культурологические аспекты современного инженерного образования» памяти кандидата педагогических наук, доцента Н.А. Качалова, Томск, 15-17 ноября 2023 г.. С. 141-148.— .— Томск: Изд-во ТПУ, 2023.— conference_tpu-2023-C85_V2.pdf |
|---|---|
| Auteur principal: | |
| Collectivité auteur: | |
| Autres auteurs: | , |
| Résumé: | 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 |
| Publié: |
2023
|
| Collection: | Актуальные векторы исследований и подходы в современной лингвистике |
| Sujets: | |
| Accès en ligne: | http://earchive.tpu.ru/handle/11683/77924 |
| Format: | Électronique Chapitre de livre |
| KOHA link: | https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=671978 |
| Résumé: | 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 |
|---|