Graphs RAG at Scale: Beyond Retrieval-Augmented Generation With Labeled Property Graphs and Resource Description Framework for Complex and Unknown Search Spaces

Manie Tadayon; Mayank Gupta

cs.IRMar 21, 2026

Graphs RAG at Scale: Beyond Retrieval-Augmented Generation With Labeled Property Graphs and Resource Description Framework for Complex and Unknown Search Spaces

Authors: Manie Tadayon, Mayank Gupta

Organizations: AI Scientist, Capital Group

Abstract

Recent advances in Retrieval-Augmented Generation (RAG) have revolutionized knowledge-intensive tasks, yet traditional RAG methods struggle when the search space is unknown or when documents are semi-structured or structured. We introduce a novel end-to-end Graph RAG framework that leverages both Labeled Property Graph (LPG) and Resource Description Framework (RDF) architectures to overcome these limitations. Our approach enables dynamic document retrieval without the need to pre-specify the number of documents and eliminates inefficient reranking. We propose an innovative method for converting documents into RDF triplets using JSON key-value pairs, facilitating seamless integration of semi-structured data. Additionally, we present a text to Cypher framework for LPG, achieving over 90% accuracy in real-time translation of text queries to Cypher, enabling fast and reliable query generation suitable for online applications. Our empirical evaluation demonstrates that Graph RAG significantly outperforms traditional embedding-based RAG in accuracy, response quality, and reasoning, especially for complex, semi-structured tasks. These findings establish Graph RAG as a transformative solution for next-generation retrieval-augmented systems.

Figures & tables

Figure 1: Overview of the RDF-based pipeline for Graph RAG.

Figure 2: Overview of the LPG-based pipeline for Graph RAG.

Method	Score
RAG 2 (Agentic RAG)	116
$\mathrm{RAG}_{\mathrm{RDF}}$	172.5
$\mathrm{RAG}_{\mathrm{LPG}}$	185.5

Table 1: Overall performance scores for each method out of 200 points.

Method	Intent	Correct	Partial	Incorrect
$\mathrm{RAG}_{2}$ (Agentic)	Search	23	31	45
$\mathrm{RAG}_{2}$ (Agentic)	Compare	32	6	7
$\mathrm{RAG}_{2}$ (Agentic)	Detail	33	3	9
$\mathrm{RAG}_{2}$ (Agentic)	Other	6	4	0
$\mathrm{RAG}_{\mathrm{RDF}}$	Search	70	20	10
$\mathrm{RAG}_{\mathrm{RDF}}$	Compare	37	8	0

Table 2: Number of correct, partial, and incorrect responses for each method and intent.

Figure 3: Sample Example of LPG Node Design

Predicate	Category
topx.topHoldings.values.nameAbbvie.name.asOfDate2025-09-30	allocation
facts.companiesIssuersDate	generic
geographicBreakdown.regions.nameEurozone.countries.nameGreece.
values.benchmarkPercent.asOfDate2025-09-30	allocation, benchmark

Table 3: Example mapping of predicates to categories.

Original Predicate	Natural Language Predicate
facts.companiesIssuers	Facts About Companies Issuers
facts.shareholderAccounts	Facts About Shareholder Accounts
descriptions.nameHoldingsOutsideTheUS.description	Description of Holdings Outside the US

Table 4: Examples of converting predicates to natural language.

Intent	Example Query
Compare	Compare AMCAP-F3 and AMCAP-R6?
Compare	Compare Balanced funds and growth funds in terms of strategy?
Detail	What is fund objective and strategy of GFA-R6?
Detail	Who are the portfollio managers for WMIF-R2 fund?
Search	List all growth funds?
Search	List the expense ratio for all balanced funds?

Table 5: Representative examples of queries for each intent category.

Figure 4: Full Graph RDF structure: This figure illustrates the complete end-to-end pipeline, including all agentic components responsible for query rewriting, normalization, similar query generation, and other orchestration steps.

Graph Retrieval-Augmented Generation

Graph Retrieval-Augmented Generation connects language models to knowledge graphs to retrieve relational evidence for grounded, multi-hop answers.

See all 229 papers

GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation
Mar 26, 2026Ruizhong Miao, Yuying Wang, Rongguang Wang +4Multi-Hop Retrieval Retrieval-Augmented Generation
Oracle AI
LiteSemRAG: Lightweight LLM-Free Semantic-Aware Graph Retrieval for Robust RAG
Mar 16, 2026Xiao Yue, Guangzhi Qu, Lige GanGraph Retrieval-Augmented Generation Graph-Based Retrieval
Oakland University, Rochester Hills, MI 48309, USA
Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems
Apr 1, 2026Dongzhe Fan, Zheyi Xue, Siyuan Liu +1Graph Retrieval-Augmented Generation RAG Evaluation
New York University Shanghai, Shanghai, China

Mar 26, 2026J/K move · Enter open · S save

GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation

Ruizhong Miao, Yuying Wang, Rongguang Wang, Chenyang Li+3

Oracle AI

Multi-Hop Retrieval Retrieval-Augmented Generation Information Retrieval Graph-Based Retrieval

Open paper AskPDF arXiv

Semantic search in retrieval-augmented generation (RAG) systems is often insufficient for complex information needs, particularly when relevant evidence is scattered across multiple sources, because it may fail to retrieve the complete set of evidence. Existing approaches to addressing this problem either rely on iterative agentic retrieval, which can be computationally inefficient, or maintain additional structures such as knowledge graphs, which introduce storage and maintenance overhead. In this paper, we propose GraphER, a graph-based enrichment and reranking framework that (1) leverages the organizational structure of data to capture proximity relationships beyond semantic similarity, (2) constructs a graph at query time based on these proximities, and (3) applies graph-based ranking to surface the top candidate documents. Experiments across table retrieval, multi-hop retrieval, and long-document retrieval benchmarks demonstrate consistent improvements in terms of retrieval completeness. Additionally, GraphER requires no additional graph infrastructure and integrates seamlessly with standard vector stores. The framework is retriever-agnostic, supports multiple forms of proximity, and introduces minimal query-time latency.

Abstract

Graph Retrieval-Augmented Generation

Explore similar work

GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation

LiteSemRAG: Lightweight LLM-Free Semantic-Aware Graph Retrieval for Robust RAG

Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems