Augmenting Question Answering with A Hybrid RAG Approach

TL;DR

This paper introduces SSRAG, a hybrid retrieval-augmented generation architecture that combines vector and graph-based retrieval techniques to significantly improve question-answering accuracy and informativeness across multiple datasets and models.

Contribution

The paper presents a novel Structured-Semantic RAG (SSRAG) architecture that integrates query augmentation, agentic routing, and hybrid retrieval methods to enhance QA performance.

Findings

SSRAG outperforms standard RAG on multiple datasets.

Improved answer accuracy and informativeness demonstrated.

Consistent gains across five large language models.

Abstract

Retrieval-Augmented Generation (RAG) has emerged as a powerful technique for enhancing the quality of responses in Question-Answering (QA) tasks. However, existing approaches often struggle with retrieving contextually relevant information, leading to incomplete or suboptimal answers. In this paper, we introduce Structured-Semantic RAG (SSRAG), a hybrid architecture that enhances QA quality by integrating query augmentation, agentic routing, and a structured retrieval mechanism combining vector and graph based techniques with context unification. By refining retrieval processes and improving contextual grounding, our approach improves both answer accuracy and informativeness. We conduct extensive evaluations on three popular QA datasets, TruthfulQA, SQuAD and WikiQA, across five Large Language Models (LLMs), demonstrating that our proposed approach consistently improves response quality over standard RAG implementations.