Enhancing Retrieval Processes for Language Generation with Augmented Queries

TL;DR

This paper improves document retrieval for language models by integrating retrieval-augmented generation with query optimization, demonstrating enhanced accuracy and efficiency across different models and scenarios.

Contribution

It introduces an innovative query optimization process combined with RAG, utilizing models like Orca2 7B and BERT with UMAP to enhance retrieval scalability and accuracy.

Findings

Significant performance improvement with RAG and prompt augmenters.

Effective document retrieval using language model-generated queries.

UMAP simplifies retrieval while maintaining strong results.

Abstract

In the rapidly changing world of smart technology, searching for documents has become more challenging due to the rise of advanced language models. 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 language models 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 language model's performance under RAG, particularly when assisted with prompts augmenters. Consistency in document retrieval across different encodings highlights the effectiveness of using language model-generated queries. The introduction of UMAP for BERT further simplifies document retrieval while maintaining strong results.