HugRAG: Hierarchical Causal Knowledge Graph Design for RAG

TL;DR

HugRAG introduces a hierarchical, causally grounded graph framework for retrieval augmented generation, improving reasoning accuracy and scalability over existing methods by explicitly modeling causal relationships.

Contribution

The paper presents HugRAG, a novel hierarchical causal knowledge graph design that enhances RAG by explicitly modeling causality and enabling scalable, structured reasoning.

Findings

HugRAG outperforms existing graph-based RAG methods across multiple datasets.

Explicit causal modeling reduces spurious correlations in generated answers.

The framework improves reasoning fidelity and scalability in large knowledge graphs.

Abstract

Retrieval augmented generation (RAG) has enhanced large language models by enabling access to external knowledge, with graph-based RAG emerging as a powerful paradigm for structured retrieval and reasoning. However, existing graph-based methods often over-rely on surface-level node matching and lack explicit causal modeling, leading to unfaithful or spurious answers. Prior attempts to incorporate causality are typically limited to local or single-document contexts and also suffer from information isolation that arises from modular graph structures, which hinders scalability and cross-module causal reasoning. To address these challenges, we propose HugRAG, a framework that rethinks knowledge organization for graph-based RAG through causal gating across hierarchical modules. HugRAG explicitly models causal relationships to suppress spurious correlations while enabling scalable reasoning over large-scale knowledge graphs. Extensive experiments demonstrate that HugRAG consistently outperforms competitive graph-based RAG baselines across multiple datasets and evaluation metrics. Our work establishes a principled foundation for structured, scalable, and causally grounded RAG systems.