Contextual Conversational Intelligence : Leveraging Language Models For College Chatbot By Retrieval Augmented Generation

Contextual Conversational Intelligence : Leveraging Language Models For College Chatbot By Retrieval Augmented Generation

Anergha K Mohan1, Thomas John2, Nikhil P S3

1,2,3 Computer Science and Engineering , Model Engineering College , Kochi , India

Abstract - By harnessing the capabilities of Large Language Models (LLM), the proposed system evolves into a sophisticated conversational agent, capable of understanding nuanced user inputs, providing context-aware responses, and delivering an unparalleled level of engagement. This chatbot is also equipped to assess a student's likelihood of being accepted into a specific program at the college using a machine learning (ML) model. The model analyzes the student's rank and eligible quota (such as reserved categories) in conjunction with historical admission data to gauge their chances of acceptance. It also recommends alternative programs where the student may have a better chance of admission based on their rank. The chatbot also features a smart Applicant Tracking System (ATS) that assists students in evaluating their resumes. This system provides keyword matching suggestions based on job descriptions and generates an overview of the resume. Additionally, it highlights areas for improvement and highlights the resume's distinctiveness. The methodology involves the development and deployment of a website chat bot integrated with Lang Chain, with the potential of advanced language models in transforming website chat bot interactions using Retrieval augmented generation (RAG) technique to ground LLM to generate responses to user queries based on a custom knowledge-base.

Key Words:  Chatbot, Generative AI, Large Langauge Model, Website, Machine Learning, Retrieval-augmented generation , Web scrapping , Resume , ATS.