SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval

TL;DR

SKETCH is a new method that combines semantic text retrieval with knowledge graphs to improve information retrieval and understanding in RAG systems, leading to more accurate and contextually relevant responses.

Contribution

It introduces SKETCH, a novel approach integrating structured knowledge graphs with semantic retrieval to enhance RAG performance and context comprehension.

Findings

Outperforms baseline methods on multiple datasets.

Achieves highest answer relevancy and context precision.

Sets new benchmarks in retrieval quality.

Abstract

Retrieval-Augmented Generation (RAG) systems have become pivotal in leveraging vast corpora to generate informed and contextually relevant responses, notably reducing hallucinations in Large Language Models. Despite significant advancements, these systems struggle to efficiently process and retrieve information from large datasets while maintaining a comprehensive understanding of the context. This paper introduces SKETCH, a novel methodology that enhances the RAG retrieval process by integrating semantic text retrieval with knowledge graphs, thereby merging structured and unstructured data for a more holistic comprehension. SKETCH, demonstrates substantial improvements in retrieval performance and maintains superior context integrity compared to traditional methods. Evaluated across four diverse datasets: QuALITY, QASPER, NarrativeQA, and Italian Cuisine-SKETCH consistently outperforms baseline approaches on key RAGAS metrics such as answer_relevancy, faithfulness, context_precision and context_recall. Notably, on the Italian Cuisine dataset, SKETCH achieved an answer relevancy of 0.94 and a context precision of 0.99, representing the highest performance across all evaluated metrics. These results highlight SKETCH's capability in delivering more accurate and contextually relevant responses, setting new benchmarks for future retrieval systems.