The press service of the university reported that the development of the tests was due to the growing interest in artificial intelligence language models that can solve a wide range of problems in the educational process. However, to fully integrate AI into pedagogy, it is necessary to carefully evaluate its capabilities and identify weaknesses. To do this, scientists have created more than 3.9 thousand tasks covering 16 areas of knowledge, including teaching methods, psychology and classroom management.
The basis for the development of tests were the methods of psychometrics – a science combining psychology, mathematics and pedagogy. An experiment with the Russian version of the GPT-4 language model showed that artificial intelligence copes well with information gathering tasks, but has difficulty solving more complex tasks that require flexibility and in-depth analysis. The model showed poor results when solving theoretical problems and adapting to new conditions.
Researchers state that this approach helps identify key problems that artificial intelligence has not yet overcome.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
