Context-augmented Retrieval: A Novel Framework for Fast Information Retrieval based Response Generation using Large Language Model

TL;DR

This paper introduces Context Augmented Retrieval (CAR), a new framework that improves the speed and relevance of information retrieval for large language model-based response generation by combining classification with vector store partitioning.

Contribution

The paper presents a novel approach that partitions the vector database via real-time classification, enhancing retrieval speed and answer relevance in RAG-based QA systems.

Findings

CAR significantly reduces retrieval and generation time.

CAR maintains high answer quality with larger corpora.

The approach outperforms traditional retrieval methods in speed and relevance.

Abstract

Generating high-quality answers consistently by providing contextual information embedded in the prompt passed to the Large Language Model (LLM) is dependent on the quality of information retrieval. As the corpus of contextual information grows, the answer/inference quality of Retrieval Augmented Generation (RAG) based Question Answering (QA) systems declines. This work solves this problem by combining classical text classification with the Large Language Model (LLM) to enable quick information retrieval from the vector store and ensure the relevancy of retrieved information. For the same, this work proposes a new approach Context Augmented retrieval (CAR), where partitioning of vector database by real-time classification of information flowing into the corpus is done. CAR demonstrates good quality answer generation along with significant reduction in information retrieval and answer generation time.