HG-RAG: Hierarchy-Guided Retrieval-Augmented Generation for Structured Knowledge Graphs

• URL: http://arxiv.org/abs/2607.14095v1
• Date: Thu, 16 Apr 2026 01:05:19 GMT
• Title: HG-RAG: Hierarchy-Guided Retrieval-Augmented Generation for Structured Knowledge Graphs
• Abstract summary: HG-RAG (Hierarchy-Guided RAG) is a framework that performs graph-traversal over a hierarchical knowledge graph to deliver structured context to a language model.<n>I evaluate HG-RAG against a dense retrieval baseline across three world scales (18-800 nodes) with four query types.<n>Results show HG-RAG consistently outperforms the flat baseline on hierarchical, relational, and multi-hop reasoning tasks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval Augmented Generation (RAG) has proven to be a widely successful process at improving the quality of outputs from a Large Language Model (LLM) for wider context. However, RAG systems typically retrieve context from flat document stores, which struggles when queries require hierarchical or relational reasoning across structured knowledge. I present HG-RAG (Hierarchy-Guided RAG), a framework that performs graph-traversal over a hierarchical knowledge graph to deliver structured context to a language model. My retrieval pipeline resolves a named entity anchor from the query, then expands context upward through parent nodes, laterally through relational neighbors, and downward through child nodes when needed. I evaluate HG-RAG against a dense retrieval baseline across three world scales (18-800 nodes) with four query types: local fact, hierarchical, neighborhood, and multi-hop. Results show HG-RAG consistently outperforms the flat baseline on hierarchical, relational, and multi-hop reasoning tasks, while reducing hallucination and maintaining locality coherence.

Related papers

• SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG [23.48941508046885]
  We present SproutRAG, an attention-guided hierarchical RAG framework.<n>It organizes sentence-level chunks into progressively larger but semantically coherent units.<n>It learns which attention heads and layers best capture semantic document structure.
  arXiv  Detail & Related papers  (2026-06-16T18:28:00Z)
• DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented Generation [35.30060374506784]
  A prevalent technical approach in this context is graph-based RAG (G-RAG)<n>We propose DA-RAG, which leverages attributed community search (ACS) to extract relevant subgraphs based on the queried question dynamically.<n>We evaluate DA-RAG on multiple datasets, demonstrating that it outperforms existing RAG methods by up to 40% in head-to-head comparisons.
  arXiv  Detail & Related papers  (2026-02-09T11:45:13Z)
• Disco-RAG: Discourse-Aware Retrieval-Augmented Generation [81.53888908988756]
  We propose Disco-RAG, a discourse-aware framework that injects discourse signals into the generation process.<n>Our method constructs intra-chunk discourse trees to capture local hierarchies and builds inter-chunk rhetorical graphs to model cross-passage coherence.<n>Experiments on question answering and long-document summarization benchmarks show the efficacy of our approach.
  arXiv  Detail & Related papers  (2026-01-07T20:32:50Z)
• Query-Centric Graph Retrieval Augmented Generation [15.423162448800134]
  QCG-RAG is a query-centric graph RAG framework that enables query-granular indexing and multi-hop chunk retrieval.<n> Experiments on LiHuaWorld and MultiHop-RAG show that QCG-RAG consistently outperforms prior chunk-based and graph-based RAG methods in question answering accuracy.
  arXiv  Detail & Related papers  (2025-09-25T14:35:44Z)
• Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching [61.824094419641575]
  Large Language Models (LLMs) struggle with hallucinations and factual errors in knowledge-intensive scenarios like knowledge graph question answering (KGQA)<n>We attribute this to the semantic gap between structured knowledge graphs (KGs) and unstructured queries, caused by inherent differences in their focuses and structures.<n>Existing methods usually employ resource-intensive, non-scalable reasoning on vanilla KGs, but overlook this gap.<n>We propose a flexible framework, Enrich-on-Graph (EoG), which leverages LLMs' prior knowledge to enrich KGs, bridge the semantic gap between graphs and queries.
  arXiv  Detail & Related papers  (2025-09-25T06:48:52Z)
• Cross-Granularity Hypergraph Retrieval-Augmented Generation for Multi-hop Question Answering [49.43814054718318]
  Multi-hop question answering (MHQA) requires integrating knowledge scattered across multiple passages to derive the correct answer.<n>Traditional retrieval-augmented generation (RAG) methods primarily focus on coarse-grained textual semantic similarity.<n>We propose a novel RAG approach called HGRAG for MHQA that achieves cross-granularity integration of structural and semantic information via hypergraphs.
  arXiv  Detail & Related papers  (2025-08-15T06:36:13Z)
• LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval [10.566901995776025]
  LeanRAG is a framework that combines knowledge aggregation and retrieval strategies.<n>It can mitigate the substantial overhead associated with path retrieval on graphs and minimizes redundant information retrieval.
  arXiv  Detail & Related papers  (2025-08-14T06:47:18Z)
• Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation [69.45495166424642]
  We develop a robust and discriminative QA benchmark to measure temporal, causal, and character consistency understanding in narrative documents.<n>We then introduce Entity-Event RAG (E2RAG), a dual-graph framework that keeps separate entity and event subgraphs linked by a bipartite mapping.<n>Across ChronoQA, our approach outperforms state-of-the-art unstructured and KG-based RAG baselines, with notable gains on causal and character consistency queries.
  arXiv  Detail & Related papers  (2025-06-06T10:07:21Z)
• Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation [79.75818239774952]
  Large language models (LLMs) have demonstrated remarkable capabilities, but still struggle with issues like hallucinations and outdated information.<n>Retrieval-augmented generation (RAG) addresses these issues by grounding LLM outputs in external knowledge with an Information Retrieval (IR) system.<n>We propose Align-GRAG, a novel reasoning-guided dual alignment framework in post-retrieval phrase.
  arXiv  Detail & Related papers  (2025-05-22T05:15:27Z)
• Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning [62.640169289390535]
  SPLIT-RAG is a multi-agent RAG framework that addresses the limitations with question-driven semantic graph partitioning and collaborative subgraph retrieval.<n>The innovative framework first create Semantic Partitioning of Linked Information, then use the Type-Specialized knowledge base to achieve Multi-Agent RAG.<n>The attribute-aware graph segmentation manages to divide knowledge graphs into semantically coherent subgraphs, ensuring subgraphs align with different query types.<n>A hierarchical merging module resolves inconsistencies across subgraph-derived answers through logical verifications.
  arXiv  Detail & Related papers  (2025-05-20T06:44:34Z)
• ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation [16.204046295248546]
  Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models.<n>We introduce a novel graph-based RAG approach, called Attributed Community-based Hierarchical RAG (ArchRAG)<n>We build a novel hierarchical index structure for the attributed communities and develop an effective online retrieval method.
  arXiv  Detail & Related papers  (2025-02-14T03:28:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.