Enhancing Retrieval Processes for Language Generation with Augmented Queries

Abstract: In the rapidly changing world of smart technology, searching for documents has become more challenging due to the rise of advanced LLMs. These models sometimes face difficulties, like providing inaccurate information, commonly known as "hallucination." This research focuses on addressing this issue through Retrieval-Augmented Generation (RAG), a technique that guides models to give accurate responses based on real facts. To overcome scalability issues, the study explores connecting user queries with sophisticated LLMs such as BERT and Orca2, using an innovative query optimization process. The study unfolds in three scenarios: first, without RAG, second, without additional assistance, and finally, with extra help. Choosing the compact yet efficient Orca2 7B model demonstrates a smart use of computing resources. The empirical results indicate a significant improvement in the initial LLM's performance under RAG, particularly when assisted with prompts augmenters. Consistency in document retrieval across different encodings highlights the effectiveness of using LLM-generated queries. The introduction of UMAP for BERT further simplifies document retrieval while maintaining strong results.