XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zhuoling, Nguyen, Ha Linh Hong Tran, Bladinieres, Valeria, Romanovsky, Maxim
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917440266436608
author Li, Zhuoling
Nguyen, Ha Linh Hong Tran
Bladinieres, Valeria
Romanovsky, Maxim
author_facet Li, Zhuoling
Nguyen, Ha Linh Hong Tran
Bladinieres, Valeria
Romanovsky, Maxim
contents Graph-based Retrieval-Augmented Generation (GraphRAG) extends traditional RAG by using knowledge graphs (KGs) to give large language models (LLMs) a structured, semantically coherent context, yielding more grounded answers. However, GraphRAG reasoning process remains a black-box, limiting our ability to understand how specific pieces of structured knowledge influence the final output. Existing explainability (XAI) methods for RAG systems, designed for text-based retrieval, are limited to interpreting an LLM response through the relational structures among knowledge components, creating a critical gap in transparency and trustworthiness. To address this, we introduce XGRAG, a novel framework that generates causally grounded explanations for GraphRAG systems by employing graph-based perturbation strategies, to quantify the contribution of individual graph components on the model answer. We conduct extensive experiments comparing XGRAG against RAG-Ex, an XAI baseline for standard RAG, and evaluate its robustness across various question types, narrative structures and LLMs. Our results demonstrate a 14.81% improvement in explanation quality over the baseline RAG-Ex across NarrativeQA, FairyTaleQA, and TriviaQA, evaluated by F1-score measuring alignment between generated explanations and original answers. Furthermore, XGRAG explanations exhibit a strong correlation with graph centrality measures, validating its ability to capture graph structure. XGRAG provides a scalable and generalizable approach towards trustworthy AI through transparent, graph-based explanations that enhance the interpretability of RAG systems.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24623
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation
Li, Zhuoling
Nguyen, Ha Linh Hong Tran
Bladinieres, Valeria
Romanovsky, Maxim
Artificial Intelligence
Information Retrieval
Machine Learning
Graph-based Retrieval-Augmented Generation (GraphRAG) extends traditional RAG by using knowledge graphs (KGs) to give large language models (LLMs) a structured, semantically coherent context, yielding more grounded answers. However, GraphRAG reasoning process remains a black-box, limiting our ability to understand how specific pieces of structured knowledge influence the final output. Existing explainability (XAI) methods for RAG systems, designed for text-based retrieval, are limited to interpreting an LLM response through the relational structures among knowledge components, creating a critical gap in transparency and trustworthiness. To address this, we introduce XGRAG, a novel framework that generates causally grounded explanations for GraphRAG systems by employing graph-based perturbation strategies, to quantify the contribution of individual graph components on the model answer. We conduct extensive experiments comparing XGRAG against RAG-Ex, an XAI baseline for standard RAG, and evaluate its robustness across various question types, narrative structures and LLMs. Our results demonstrate a 14.81% improvement in explanation quality over the baseline RAG-Ex across NarrativeQA, FairyTaleQA, and TriviaQA, evaluated by F1-score measuring alignment between generated explanations and original answers. Furthermore, XGRAG explanations exhibit a strong correlation with graph centrality measures, validating its ability to capture graph structure. XGRAG provides a scalable and generalizable approach towards trustworthy AI through transparent, graph-based explanations that enhance the interpretability of RAG systems.
title XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation
topic Artificial Intelligence
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2604.24623