Retrieval-Augmented Generation with Graphs (GraphRAG)

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

1. Very close Review Not relevant

   A Survey on Graph-Based Retrieval-Augmented Generation: Architectures, Methods, and Applications

   T. Chowdhury · 2026 · International Journal on Computational Modelling Applications · Not summarized yet

   A Survey on Graph-Based Retrieval-Augmented Generation reviews Graph-RAG architectures, methods, and applications, alongside this paper’s survey of GraphRAG concepts and domain-specific techniques.

   Abstract

   Retrieval-Augmented Generation (RAG) stands out as a promising paradigm that can be applied to improve large language models by serving text generation with external sources of knowledge. Nevertheless, traditional RAG models are mostly based on flat text corpora and similarity-based retrieval and thus are not able to realize intricate relations, multi-hop dependencies, and structured semantics. The survey provides a high-level introduction to graph-based Retrieval-Augmented Generation (Graph-RAG), which is an emerging methodology adding systematic knowledge representations to the retrieval and generation process. Graph-RAG supports relational knowledge reasoning, contextual cohesion and expl…

2. Very close Builds on this paper Cites this paper Not relevant

   RAG vs. GraphRAG: A Systematic Evaluation and Key Insights

   Hao-Yu Han, Li Ma, Yu Wang et al. · 2025 · Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · cited 118 times · Not summarized yet

   RAG vs. GraphRAG evaluates text-based RAG and GraphRAG systems and cites this survey.

   Abstract

   Retrieval-Augmented Generation (RAG) improves large language models (LLMs) by retrieving relevant information from external sources and has been widely adopted for text-based tasks. For structured data, such as knowledge graphs, Graph Retrieval-Augmented Generation (GraphRAG) retrieves and aggregates information along graph structures. More recently, GraphRAG has been extended to general text settings by organizing unstructured text into graph representations, showing promise for reasoning and grounding. Despite these advances, existing GraphRAG systems for text data are often tailored to specific tasks, datasets, and system designs, resulting in heterogeneous evaluation protocols. Consequen…

3. Very close Builds on this paper Cites this paper Uses this paper in depth Not relevant

   When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation

   Zhi-Shang Xiang, Chuan-Yu Wu, Qing-Gang Zhang et al. · 2025 · arXiv.org · preprint, not peer reviewed · cited 60 times · Not summarized yet

   When to use Graphs in RAG introduces a benchmark to test when graph structures benefit RAG and cites this survey.

   Abstract

   Graph retrieval-augmented generation (GraphRAG) has emerged as a powerful paradigm for enhancing large language models (LLMs) with external knowledge. It leverages graphs to model the hierarchical structure between specific concepts, enabling more coherent and effective knowledge retrieval for accurate reasoning.Despite its conceptual promise, recent studies report that GraphRAG frequently underperforms vanilla RAG on many real-world tasks. This raises a critical question: Is GraphRAG really effective, and in which scenarios do graph structures provide measurable benefits for RAG systems? To address this, we propose GraphRAG-Bench, a comprehensive benchmark designed to evaluate GraphRAG mode…

4. Very close Review Not relevant

   Graph Retrieval-Augmented Generation: A Survey

   Boci Peng, Yun Zhu, Yong-Chao Liu et al. · 2024 · ACM Trans. Inf. Syst. · cited 695 times · Not summarized yet

   Graph Retrieval-Augmented Generation: A Survey reviews GraphRAG’s use of graph structure for relational retrieval, the subject of this survey.

   Abstract

   Recently, Retrieval-Augmented Generation (RAG) has achieved remarkable success in addressing the challenges of Large Language Models (LLMs) without necessitating retraining. By referencing an external knowledge base, RAG refines LLM outputs, effectively mitigating issues such as “hallucination,” lack of domain-specific knowledge, and outdated information. However, the complex structure of relationships among different entities in databases presents challenges for RAG systems. In response, GraphRAG leverages structural information across entities to enable more precise and comprehensive retrieval, capturing relational knowledge and facilitating more accurate, context-aware responses. Given th…

5. Very close Another approach to the problem Not relevant

   GRAG: Graph Retrieval-Augmented Generation

   Yun-Tong Hu, Zhihan Lei, Zheng Zhang et al. · 2024 · North American Chapter of the Association for Computational Linguistics · cited 188 times · Not summarized yet

   GRAG proposes divide-and-conquer retrieval of textual subgraphs to combine textual and topological information for generation.

   Abstract

   Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and, as a result, falls short in handling networked documents which are very popular in many applications such as citation graphs, social media, and knowledge graphs. To overcome this limitation, we introduce Graph Retrieval-Augmented Generation (GRAG), which tackles the fundamental challenges in retrieving textual subgraphs and integrating the joint textual and topological information into Large Language Models (LLMs) to enhance its generation. To enable efficient textual subgraph retrieval, we propose a novel divide-and-conquer strategy that retrieves the optimal subgraph structure in linear time. T…

6. Very close Builds on this paper Cites this paper Uses this paper in depth Not relevant

   Evaluation of GraphRAG Strategies for Efficient Information Retrieval

   Asma Houimli, Zaineb Gabsi, S. Skhiri · 2025 · BigData Congress [Services Society] · cited 1 time · Not summarized yet

   Evaluation of GraphRAG Strategies compares GraphRAG retrieval strategies and cites this survey.

   Abstract

   Retrieval Augmented Generation (RAG) has emerged as a solution to enhance large language models (LLMs) and avoid hallucination by grounding their answers in external data. However, traditional RAG systems struggle to capture relationships and cross-references between different sources unless explicitly mentioned. This challenge is common in real-world scenarios, where information is often distributed and interlinked, making graphs a more effective representation. Recent research has focused on using GraphRAG systems that retrieve subgraphs instead of isolated passages, improving both interpretability and retrieval precision. Our work provides a technical contribution through a comparative ev…

7. Very close Broader context Not relevant

   Retrieval-Augmented Generation for AI-Generated Content: A Survey

   Penghao Zhao, Hailin Zhang, Qinhan Yu et al. · 2024 · Computer Vision and Pattern Recognition · cited 781 times · AI summary available

   Retrieval-Augmented Generation for AI-Generated Content surveys RAG broadly, including its role in improving generated content.

   Abstract

   Advancements in model algorithms, the growth of foundational models, and access to high-quality datasets have propelled the evolution of Artificial Intelligence Generated Content (AIGC). Despite its notable successes, AIGC still faces hurdles such as updating knowledge, handling long-tail data, mitigating data leakage, and managing high training and inference costs. Retrieval-Augmented Generation (RAG) has recently emerged as a paradigm to address such challenges. In particular, RAG introduces the information retrieval process, which enhances the generation process by retrieving relevant objects from available data stores, leading to higher accuracy and better robustness. In this paper, we c…

8. Very close Builds on this paper Cites this paper Not relevant

   NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes

   Tianyang Xu, Haojie Zheng, Cheng-Ze Li et al. · 2025 · arXiv.org · preprint, not peer reviewed · cited 29 times · Not summarized yet

   NodeRAG proposes heterogeneous graph nodes to structure graph-based RAG and cites this survey.

   Abstract

   Retrieval-augmented generation (RAG) empowers large language models to access external and private corpus, enabling factually consistent responses in specific domains. By exploiting the inherent structure of the corpus, graph-based RAG methods further enrich this process by building a knowledge graph index and leveraging the structural nature of graphs. However, current graph-based RAG approaches seldom prioritize the design of graph structures. Inadequately designed graph not only impede the seamless integration of diverse graph algorithms but also result in workflow inconsistencies and degraded performance. To further unleash the potential of graph for RAG, we propose NodeRAG, a graph-cent…

Papers that cite it

1. Very close Builds on this paper Uses this paper in depth Not relevant

   Multi-Agent GraphRAG: A Text-to-Cypher Framework for Labeled Property Graphs

   Anton Gusarov, A. Volkova, Valentin Khrulkov et al. · 2025 · arXiv.org · preprint, not peer reviewed · cited 8 times · Not summarized yet

   Multi-Agent GraphRAG develops a text-to-Cypher system for labeled property graphs and cites this survey.

   Abstract

   While Retrieval-Augmented Generation (RAG) methods commonly draw information from unstructured documents, the emerging paradigm of GraphRAG aims to leverage structured data such as knowledge graphs. Most existing GraphRAG efforts focus on Resource Description Framework (RDF) knowledge graphs, relying on triple representations and SPARQL queries. However, the potential of Cypher and Labeled Property Graph (LPG) databases to serve as scalable and effective reasoning engines within GraphRAG pipelines remains underexplored in current research literature. To fill this gap, we propose Multi-Agent GraphRAG, a modular LLM agentic system for text-to-Cypher query generation serving as a natural langua…

2. Very close Builds on this paper Not relevant

   GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation

   Lin-Hao Luo, Zi-Cheng Zhao, G. Haffari et al. · 2025 · Neural Information Processing Systems · cited 64 times · Not summarized yet

   GFM-RAG proposes a graph foundation model for retrieval and cites this survey.

   Abstract

   Retrieval-augmented generation (RAG) has proven effective in integrating knowledge into large language models (LLMs). However, conventional RAGs struggle to capture complex relationships between pieces of knowledge, limiting their performance in intricate reasoning that requires integrating knowledge from multiple sources. Recently, graph-enhanced retrieval augmented generation (GraphRAG) builds graph structure to explicitly model these relationships, enabling more effective and efficient retrievers. Nevertheless, its performance is still hindered by the noise and incompleteness within the graph structure. To address this, we introduce GFM-RAG, a novel graph foundation model (GFM) for retrie…

3. Very close Review Not relevant

   Graph-Based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey

   Zu-Lun Zhu, Tian-Cheng Huang, Kai Wang et al. · 2025 · ACM Computing Surveys · cited 43 times · Not summarized yet

   Graph-Based Approaches and Functionalities surveys graph techniques for RAG and cites this survey.

   Abstract

   Large language models (LLMs) struggle with the factual error during inference due to the lack of sufficient training data and the most updated knowledge, leading to the hallucination problem. Retrieval-Augmented Generation (RAG) has gained attention as a promising solution to address the limitation of LLMs, by retrieving relevant information from external source to generate more accurate answers to the questions. Given the pervasive presence of structured knowledge in the external source, considerable strides in RAG have been made to employ the techniques related to graphs and achieve more complex reasoning based on the topological information between knowledge entities. Although recent surv…

4. Very close Builds on this paper Not relevant

   GraphRAG Under Fire

   Jiacheng Liang, Yuhui Wang, Changjiang Li et al. · 2025 · IEEE Symposium on Security and Privacy · cited 33 times · Not summarized yet

   GraphRAG Under Fire studies poisoning vulnerabilities in GraphRAG and cites this survey.

   Abstract

   GraphRAG advances retrieval-augmented generation (RAG) by structuring external knowledge as multi-scale knowledge graphs, enabling language models to integrate both broad context and granular details in their generation. While GraphRAG has demonstrated success across domains, its security implications remain largely unexplored. To bridge this gap, this work examines GraphRAG's vulnerability to poisoning attacks, uncovering an intriguing security paradox: existing RAG poisoning attacks are less effective under GraphRAG than conventional RAG, due to GraphRAG's graph-based indexing and retrieval; yet, the same features also create new attack surfaces. We present GragPoison, a novel attack that …

5. Very close Review Not relevant

   A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions

   Agada Joseph Oche, Ademola Glory Folashade, Tirthankar Ghosal et al. · 2025 · arXiv.org · preprint, not peer reviewed · cited 86 times · Not summarized yet

   A Systematic Review of Key RAG Systems surveys RAG broadly, including its evolution and technical components.

   Abstract

   Retrieval-Augmented Generation (RAG) represents a major advancement in natural language processing (NLP), combining large language models (LLMs) with information retrieval systems to enhance factual grounding, accuracy, and contextual relevance. This paper presents a comprehensive systematic review of RAG, tracing its evolution from early developments in open domain question answering to recent state-of-the-art implementations across diverse applications. The review begins by outlining the motivations behind RAG, particularly its ability to mitigate hallucinations and outdated knowledge in parametric models. Core technical components-retrieval mechanisms, sequence-to-sequence generation mode…