top of page

TEAM

Improving RAG by Averaging

Qidu(Quentin) Fu, Gilyoung Cheong, Sixuan Lou, Junichi Koganemaru, Dapeng Shang, XINYUAN LAI

clear.png

We implement a specific pipeline of Retrieval-Augmented Generation (RAG) for a question answering machine using SBERT developed by Nils Reimers and Iryna Gurevych based on Google's BERT. Experimentally, we show that the one we implement (averaging RAG) is better than the other baseline one (naïve RAG) in retrieval based on two reasonable relative performance metrics. In the retrieval process, we also apply K-Means Clustering to reduce the runtime significantly.

Screen Shot 2022-06-03 at 11.31.35 AM.png
github URL
bottom of page