Knowledge Pyramid Construction for Multi-Level Retrieval-Augmented Generation

TL;DR

This paper introduces a multi-layer knowledge pyramid for retrieval-augmented generation to improve answer precision, employing cross-layer techniques and benchmarks, significantly enhancing GPT-4's performance.

Contribution

It proposes a novel multi-layer knowledge pyramid framework with dynamic updates and filtering, advancing retrieval-augmented generation methods.

Findings

Outperforms 19 state-of-the-art methods in experiments.

Achieves 395% F1 score improvement on GPT-4.

Introduces two domain-specific knowledge retrieval benchmarks.

Abstract

This paper addresses the need for improved precision in existing knowledge-enhanced question-answering frameworks, specifically Retrieval-Augmented Generation (RAG) methods that primarily focus on enhancing recall. We propose a multi-layer knowledge pyramid approach within the RAG framework to achieve a better balance between precision and recall. The knowledge pyramid consists of three layers: Ontologies, Knowledge Graphs (KGs), and chunk-based raw text. We employ cross-layer augmentation techniques for comprehensive knowledge coverage and dynamic updates of the Ontology schema and instances. To ensure compactness, we utilize cross-layer filtering methods for knowledge condensation in KGs. Our approach, named PolyRAG, follows a waterfall model for retrieval, starting from the top of the pyramid and progressing down until a confident answer is obtained. We introduce two benchmarks for domain-specific knowledge retrieval, one in the academic domain and the other in the financial domain. The effectiveness of the methods has been validated through comprehensive experiments by outperforming 19 SOTA methods. An encouraging observation is that the proposed method has augmented the GPT-4, providing 395% F1 gain by improving its performance from 0.1636 to 0.8109.