Contemporary graph-based retrieval-augmented generation (RAG) methods typically begin by extracting entities from user queries and then leverage pre-constructed knowledge graphs to retrieve related relationships and metadata. However, this pipeline's exclusive reliance on entity-level extraction can lead to the misinterpretation or omission of latent yet critical information and relations. As a result, retrieved content may be irrelevant or contradictory, and essential knowledge may be excluded, exacerbating hallucination risks and degrading the fidelity of generated responses. To address these limitations, we introduce PankRAG, a framework that combines a globally aware, hierarchical query-resolution strategy with a novel dependency-aware reranking mechanism. PankRAG first constructs a multi-level resolution path that captures both parallel and sequential interdependencies within a query, guiding large language models (LLMs) through structured reasoning. It then applies its dependency-aware reranker to exploit the dependency structure among resolved sub-questions, enriching and validating retrieval results for subsequent sub-questions. Empirical evaluations demonstrate that PankRAG consistently outperforms state-of-the-art approaches across multiple benchmarks, underscoring its robustness and generalizability.
View on arXiv@article{li2025_2506.11106,
title={ Graph-based RAG Enhancement via Global Query Disambiguation and Dependency-Aware Reranking },
author={ Ningyuan Li and Junrui Liu and Yi Shan and Minghui Huang and Tong Li },
journal={arXiv preprint arXiv:2506.11106},
year={ 2025 }
}