Development of an RAG-Based LLM Chatbot for Enhancing Technical Support Service

Abstract

The global shortage of manpower for technical support is a critical issue in the digital transformation era. Recently, Large Language Models (LLMs) have made significant strides in natural language processing, leading to the development of AI chatbots to address this problem. However, LLMs have notable limitations in handling domain-specific information, often generating incorrect responses when queries go beyond the coverage of the training data or require the most up-to-date information. A promising solution is the Retrieval-Augmented Generation (RAG) approach, which incorporates domain-specific data retrieval into the generative process. Our team has developed a domain-specific and RAG-based LLM chatbot to enhance the software house technical support of an IT consultant in Canada. The chatbot was implemented and evaluated in real-world production environments. Preliminary results show that the system has achieved high scores of 38%, 188%, and 40% in the ROUGE-I, ROUGE-2, and ROUGE-L measures, respectively, compared to using only a general LLM model. End-user feedback also reflected that the enhanced system produced more accurate and efficient replies, thereby enhancing overall customer satisfaction.