PankRAG: Enhancing Graph Retrieval via Globally Aware Query Resolution and Dependency-Aware Reranking Mechanism

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Ningyuan, Liu, Junrui, Shan, Yi, Huang, Minghui, Gong, Ziren, Li, Tong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908777666576384
author Li, Ningyuan
Liu, Junrui
Shan, Yi
Huang, Minghui
Gong, Ziren
Li, Tong
author_facet Li, Ningyuan
Liu, Junrui
Shan, Yi
Huang, Minghui
Gong, Ziren
Li, Tong
contents Recent graph-based RAG approaches leverage knowledge graphs by extracting entities from a query to fetch their associated relationships and metadata. However, relying solely on entity extraction often results in the misinterpretation or omission of latent critical information and relationships. This can lead to the retrieval of irrelevant or contradictory content, as well as the exclusion of essential information, thereby increasing hallucination risks and undermining the quality of generated responses. In this paper, we propose PankRAG, a framework designed to capture and resolve the latent relationships within complex queries that prior methods overlook. It achieves this through a synergistic combination of a globally-aware hierarchical resolution pathway and a dependency-aware reranking mechanism. PankRAG first generates a globally aware resolution pathway that captures parallel and progress relationships, guiding LLMs to resolve queries through a hierarchical reasoning path. Additionally, its dependency-aware reranking mechanism utilizes resolved sub-question dependencies to augment and validate the retrieved content of the current unresolved sub-question. Experimental results demonstrate that PankRAG consistently outperforms existing state-of-the-art methods, underscoring its generalizability.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11106
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PankRAG: Enhancing Graph Retrieval via Globally Aware Query Resolution and Dependency-Aware Reranking Mechanism
Li, Ningyuan
Liu, Junrui
Shan, Yi
Huang, Minghui
Gong, Ziren
Li, Tong
Computation and Language
Artificial Intelligence
Information Retrieval
Recent graph-based RAG approaches leverage knowledge graphs by extracting entities from a query to fetch their associated relationships and metadata. However, relying solely on entity extraction often results in the misinterpretation or omission of latent critical information and relationships. This can lead to the retrieval of irrelevant or contradictory content, as well as the exclusion of essential information, thereby increasing hallucination risks and undermining the quality of generated responses. In this paper, we propose PankRAG, a framework designed to capture and resolve the latent relationships within complex queries that prior methods overlook. It achieves this through a synergistic combination of a globally-aware hierarchical resolution pathway and a dependency-aware reranking mechanism. PankRAG first generates a globally aware resolution pathway that captures parallel and progress relationships, guiding LLMs to resolve queries through a hierarchical reasoning path. Additionally, its dependency-aware reranking mechanism utilizes resolved sub-question dependencies to augment and validate the retrieved content of the current unresolved sub-question. Experimental results demonstrate that PankRAG consistently outperforms existing state-of-the-art methods, underscoring its generalizability.
title PankRAG: Enhancing Graph Retrieval via Globally Aware Query Resolution and Dependency-Aware Reranking Mechanism
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2506.11106