{"slug": "hg-rag-hierarchy-guided-retrieval-augmented-generation-for-structured-knowledge", "title": "HG-RAG: Hierarchy-Guided Retrieval-Augmented Generation for Structured Knowledge Graphs", "summary": "Researchers introduced HG-RAG, a framework that enhances retrieval-augmented generation by traversing hierarchical knowledge graphs to provide structured context to large language models. In evaluations across three world scales and four query types, HG-RAG outperformed flat retrieval baselines on hierarchical, relational, and multi-hop reasoning tasks while reducing hallucination.", "body_md": "arXiv:2607.14095v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/hg-rag-hierarchy-guided-retrieval-augmented-generation-for-structured-knowledge", "canonical_source": "https://arxiv.org/abs/2607.14095", "published_at": "2026-07-17 04:00:00+00:00", "updated_at": "2026-07-17 04:26:31.010934+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "natural-language-processing", "ai-research"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/hg-rag-hierarchy-guided-retrieval-augmented-generation-for-structured-knowledge", "markdown": "https://wpnews.pro/news/hg-rag-hierarchy-guided-retrieval-augmented-generation-for-structured-knowledge.md", "text": "https://wpnews.pro/news/hg-rag-hierarchy-guided-retrieval-augmented-generation-for-structured-knowledge.txt", "jsonld": "https://wpnews.pro/news/hg-rag-hierarchy-guided-retrieval-augmented-generation-for-structured-knowledge.jsonld"}}