Application of Large Language Models for Intent Mining in Goal-Oriented Dialogue Systems
Alexander Shukhman, Vadim R. Badikov, Leonid V. Legashev · 2024
Modern machine learning techniques in the natural language processing domain can be used to automatically generate scripts for goal-oriented dialogue systems. In this article we present a general framework for studying the automatic generation of scripts for goal-oriented dialogue systems. One of the promising methods is to extract knowledge from large language models based on prepared text prompts. We conduct a study of five popular large language models with English and Russian prompts and draws conclusions about the advisability of using certain models to solve specific problems of goal-oriented dialogue systems.