Context Awareness Gate For Retrieval Augmented Generation

TL;DR

This paper introduces the Context Awareness Gate (CAG), a novel mechanism that dynamically filters external context in Retrieval Augmented Generation to improve relevance and answer quality in open-domain question answering.

Contribution

The paper presents CAG, a new architecture that adjusts LLM inputs based on query context, and introduces Vector Candidates, a scalable, LLM-independent method for improving context relevance.

Findings

CAG effectively reduces irrelevant information retrieval.

Vector Candidates enhances scalability and independence from LLMs.

Statistical analysis of context-question relationships informs better retrieval strategies.

Abstract

Retrieval Augmented Generation (RAG) has emerged as a widely adopted approach to mitigate the limitations of large language models (LLMs) in answering domain-specific questions. Previous research has predominantly focused on improving the accuracy and quality of retrieved data chunks to enhance the overall performance of the generation pipeline. However, despite ongoing advancements, the critical issue of retrieving irrelevant information -- which can impair the ability of the model to utilize its internal knowledge effectively -- has received minimal attention. In this work, we investigate the impact of retrieving irrelevant information in open-domain question answering, highlighting its significant detrimental effect on the quality of LLM outputs. To address this challenge, we propose the Context Awareness Gate (CAG) architecture, a novel mechanism that dynamically adjusts the LLMs' input prompt based on whether the user query necessitates external context retrieval. Additionally, we introduce the Vector Candidates method, a core mathematical component of CAG that is statistical, LLM-independent, and highly scalable. We further examine the distributions of relationships between contexts and questions, presenting a statistical analysis of these distributions. This analysis can be leveraged to enhance the context retrieval process in Retrieval Augmented Generation (RAG) systems.