Program Type

Undergraduate

Faculty Advisor

Dr. Robin Ghosh

Document Type

Presentation

Location

Face-to-face

Start Date

18-4-2024 9:40 AM

End Date

18-4-2024 10:10 AM

Abstract

The advent of large language models (LLMs) such as Chat-GPT and Bard marks a significant milestone in knowledge acquisition, offering a streamlined alternative to the traditionally labor-intensive process of navigating through multiple checkpoints on the web. This emerging trend in LLMs renders the prevalent rule-based chatbots, commonly utilized by universities, increasingly outdated and subpar. This research project proposes integrating LLM technology into university websites, specifically targeting the needs of students seeking information about their institutions by introducing PUAA (Personal University AI Assistant). Our approach involves using the Retrieval-Augmented Generation (RAG) framework, leveraging the capabilities of the LlamaIndex in conjunction with state-of-the-art LLMs such as Mistral-7B provided by the Hugging Face. To quantify the effectiveness of this integration, we have employed a comprehensive set of metrics, which includes user satisfaction rates and accuracy in information retrieval. PUAA enhances the student's experience by providing instant, accurate information and reduces the workload on administrative staff, allowing them to focus on more complex inquiries and tasks. This endeavor aims to pioneer AI adoption in educational institutions, demonstrating the viability and benefits of advanced AI tools in enhancing the academic experience and information accessibility for students and staff.

Share

COinS
 
Apr 18th, 9:40 AM Apr 18th, 10:10 AM

Optimizing Campus Chat-bot Experience Using PUAA: Integrating Large Language Model (LLM) into University AI Assistants

Face-to-face

The advent of large language models (LLMs) such as Chat-GPT and Bard marks a significant milestone in knowledge acquisition, offering a streamlined alternative to the traditionally labor-intensive process of navigating through multiple checkpoints on the web. This emerging trend in LLMs renders the prevalent rule-based chatbots, commonly utilized by universities, increasingly outdated and subpar. This research project proposes integrating LLM technology into university websites, specifically targeting the needs of students seeking information about their institutions by introducing PUAA (Personal University AI Assistant). Our approach involves using the Retrieval-Augmented Generation (RAG) framework, leveraging the capabilities of the LlamaIndex in conjunction with state-of-the-art LLMs such as Mistral-7B provided by the Hugging Face. To quantify the effectiveness of this integration, we have employed a comprehensive set of metrics, which includes user satisfaction rates and accuracy in information retrieval. PUAA enhances the student's experience by providing instant, accurate information and reduces the workload on administrative staff, allowing them to focus on more complex inquiries and tasks. This endeavor aims to pioneer AI adoption in educational institutions, demonstrating the viability and benefits of advanced AI tools in enhancing the academic experience and information accessibility for students and staff.