RAG-Based LLM Chatbot Using Llama-2

Chatbots, otherwise known as autonomous conversational agents, are a rising utilitarian application of Natural Language Processing. They enable the streamlining of information searches and improve user productivity and experience. This study focuses on building a chatbot that is aimed at assisting victims of sexual harassment, using a Large Language Model (LLM). While ML-based chatbots are a notable prospect, LLM-powered chatbots offer more human-like conversations and can surpass humans in empathy. This project evaluated the performance of the LLM Llama-2 model in generating accurate and empathetic answers to create a supportive, sensitive, and informative chatbot for the victims of sexual harassment. The model leverages Retrieval Augmented generation to achieve a commendable accuracy of above 95%, providing information in an understanding and helpful tone. The model is also capable of providing helpful advice without judgement or preconceived notions about the victim, one of the reasons victims do not report their harassers.