Optimalisasi Aplikasi Chatbot Feminacare Menggunakan Model Seallm

ABSTRACT Feminacare, a women's health consultation application with a chatbot, previously used the LSTM model which had an accuracy of 61% but often gave less relevant responses. This research proposes the use of SeaLLM model with Retrieval-Augmented Generation (RAG) approach to improve the accuracy of the chatbot. Based on three trials in the evaluation of 120 questions, the chatbot obtained …