mlsanityData to 14 Oct 2026

Structure Over Scale: Schema-Constrained Causal Graphs for RAG

arXiv 2607.22592 ↗First posted 10 Jun 2026cs.AI cs.CL cs.IRcited by 0

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Graph-based retrieval-augmented generation (GraphRAG) grounds answers in structured knowledge, but current systems extract entities and relationships exhaustively, producing graphs whose size and construction cost scale with corpus length rather than with the reasoning a query requires. We introduce HCG-RAG (Hierarchical Causal Graph RAG), which replaces open-ended extraction with schema-constrained causal graphs: an automated pipeline distills a corpus into a fixed, typed vocabulary of causal variables and materializes a compact two-tier graph over it. Our schema-constrained graphs match entity-relation baselines on answer quality at a fraction of the cost: 3-20x fewer nodes, 8x-135x fewer build-time LLM calls than the most LLM-intensive baseline (MS-GraphRAG), and graphs compact enough for a domain expert to audit, correct, and extend. On medical and clinical benchmarks, including a neurologist-validated epilepsy dataset, HCG-RAG matches or exceeds the best entity-relation systems. An ablation isolates the causal graph as a structured retrieval filter, contributing +6 percentage points (pp) over embedding-only retrieval. Across all domains with discoverable hierarchical causal structure, only methods imposing higher-level organization outperform flat entity-relation retrieval, indicating that what is placed in the graph matters more than how many nodes it contains.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 21 of its 28 references that are in the map. First posted on arXiv 10 Jun 2026.

Builds on

21 of 28 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation6 Jun
  2. 2025CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation25 Mar
  3. 2024LightRAG: Simple and Fast Retrieval-Augmented Generation8 Oct
  4. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  5. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering12 Feb

Other references · 16

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  7. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  8. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  9. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  10. 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 543
  11. 2023Active Retrieval Augmented Generationcited by 516
  12. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 353
4 more
  1. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 184
  2. 2023CLadder: Assessing Causal Reasoning in Language Modelscited by 107
  3. 2020UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answeringcited by 61
  4. 2024Efficient Causal Graph Discovery Using Large Language Modelscited by 53

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026CausalRAG2: Hierarchical Causal Knowledge Graph Design for RAG
  2. 2025Causal Graphs Meet Thoughts: Enhancing Complex Reasoning in Graph-Augmented LLMs
  3. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  4. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
  5. 2026HG-RAG: Hierarchy-Guided Retrieval-Augmented Generation for Structured Knowledge Graphs
  6. 2025MedCoT-RAG: Causal Chain-of-Thought RAG for Medical Question Answering
  7. 2026MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation
  8. 2025Clue-RAG: Towards Accurate and Cost-Efficient Graph-based RAG via Multi-Partite Graph and Query-Driven Iterative Retrieval