HySemRAG: A Hybrid Semantic Retrieval-Augmented Generation Framework for Automated Literature Synthesis and Methodological Gap Analysis

TL;DR

HySemRAG is a comprehensive framework that automates large-scale literature synthesis and gap analysis by integrating advanced retrieval, document processing, and knowledge graph techniques, improving accuracy and traceability in scientific review.

Contribution

The paper introduces HySemRAG, a novel hybrid retrieval-augmented generation system with multi-layered retrieval, agentic self-correction, and knowledge graph integration for automated literature synthesis.

Findings

Semantic field extraction improved by 35.1% in similarity scores.

Agentic quality assurance achieved 68.3% success rate in single-pass responses.

System demonstrated effective gap analysis in geospatial epidemiology literature.

Abstract

We present HySemRAG, a framework that combines Extract, Transform, Load (ETL) pipelines with Retrieval-Augmented Generation (RAG) to automate large-scale literature synthesis and identify methodological research gaps. The system addresses limitations in existing RAG architectures through a multi-layered approach: hybrid retrieval combining semantic search, keyword filtering, and knowledge graph traversal; an agentic self-correction framework with iterative quality assurance; and post-hoc citation verification ensuring complete traceability. Our implementation processes scholarly literature through eight integrated stages: multi-source metadata acquisition, asynchronous PDF retrieval, custom document layout analysis using modified Docling architecture, bibliographic management, LLM-based field extraction, topic modeling, semantic unification, and knowledge graph construction. The system creates dual data products - a Neo4j knowledge graph enabling complex relationship queries and Qdrant vector collections supporting semantic search - serving as foundational infrastructure for verifiable information synthesis. Evaluation across 643 observations from 60 testing sessions demonstrates structured field extraction achieving 35.1% higher semantic similarity scores (0.655 $\pm$ 0.178) compared to PDF chunking approaches (0.485 $\pm$ 0.204, p < 0.000001). The agentic quality assurance mechanism achieves 68.3% single-pass success rates with 99.0% citation accuracy in validated responses. Applied to geospatial epidemiology literature on ozone exposure and cardiovascular disease, the system identifies methodological trends and research gaps, demonstrating broad applicability across scientific domains for accelerating evidence synthesis and discovery.