Large Language Models and Rule-Based Approaches in Domain-Specific Communication

Large Language Models and Rule-Based Approaches in Domain-Specific Communication

Mr Pradeep Nayak1,Suhas S2,Sujal Shyam Bandekar3,Tejaswini A S4,Thulasi5,Vidyashree6

Faculty,Department of Information Science And Engineering1

Students,Department  of Information Science And Engineering2,3,4,5,6

Alva’s Institute of Engineering and Technology,Mijar,Manglore,Karnataka,India

Email:thulasipoojary2005@gmail.com,Tel:7411249511

Abstract: At the moment, artificial intelligence is causing a flurry once more. Across a range of natural language processing tasks, Generative Pre-trained Transformers (GPT) models demonstrate exceptional efficacy. These days, a variety of GPT models are frequently employed to increase productivity. Using services based on the GPT framework, developers create complex software solutions, graphic departments create art designs, and numerous other industries are following suit and incorporating these new toolkits into their operations. But in several fields of natural language processing, a straightforward approach is frequently more appropriate and successful than the large language models that are currently in use. We choose to examine and contrast the real-world applications of J-Large, one of the more well-known GPT solutions, with the straightforward rulebased model in this paper.We put it into practice. We included these two concepts into a private company's internal information system that focuses on customer communication in the gaming sector. The same dataset—a log of verbal exchanges over the previous two years in the system in question—was used to train both models.