Large Fourth-Generation Language Models as a New Tool in Scientific Research

Abstract

In this study, the latest achievements in the field of deep learning, including convolutional, recurrent, and graph neural networks and attention mechanisms, as well as their contribution to the development of pre-trained language models, are examined. A brief literature review is presented, discussing the use of pre-trained language models in scientific research and education in various fields of science. Experiments are conducted on the application of ChatGPT in the field of economics. The authors present an analysis of the advantages and limitations associated with ChatGPT, providing recommendations for its use in scientific work. Additionally, the article demonstrates the ability of ChatGPT to generate C# programs for agent-based models (ABM) and computable general equilibrium (CGE) models, highlighting its potential for interdisciplinary research and practical applications in economics and computational modeling.