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

TL;DR

PankRAG introduces a novel framework that improves graph retrieval for complex queries by capturing latent relationships through hierarchical resolution and dependency-aware reranking, leading to more accurate and relevant responses.

Contribution

It presents a globally-aware hierarchical resolution pathway combined with dependency-aware reranking, addressing limitations of entity-based retrieval methods in complex query understanding.

Findings

Outperforms existing state-of-the-art methods in graph retrieval tasks.

Effectively captures latent relationships in complex queries.

Enhances the relevance and accuracy of retrieved content.

Abstract

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.