KatzBot: Revolutionizing Academic Chatbot for Enhanced Communication
This addresses the need for better information access for students, alumni, and stakeholders in academic settings, though it appears incremental as it builds on existing LLM technology.
The paper tackles the problem of poor communication in universities by developing KatzBot, a chatbot powered by a custom LLM fine-tuned on academic data, which outperforms existing open-source LLMs in accuracy and domain relevance.
Effective communication within universities is crucial for addressing the diverse information needs of students, alumni, and external stakeholders. However, existing chatbot systems often fail to deliver accurate, context-specific responses, resulting in poor user experiences. In this paper, we present KatzBot, an innovative chatbot powered by KatzGPT, a custom Large Language Model (LLM) fine-tuned on domain-specific academic data. KatzGPT is trained on two university-specific datasets: 6,280 sentence-completion pairs and 7,330 question-answer pairs. KatzBot outperforms established existing open source LLMs, achieving higher accuracy and domain relevance. KatzBot offers a user-friendly interface, significantly enhancing user satisfaction in real-world applications. The source code is publicly available at \url{https://github.com/AiAI-99/katzbot}.