Search papers, labs, and topics across Lattice.
This paper introduces XGRAG, a framework for generating causally grounded explanations for GraphRAG systems by employing graph-based perturbation strategies to quantify the contribution of individual graph components on the model answer. XGRAG addresses the limitations of existing XAI methods for RAG systems by interpreting LLM responses through the relational structures among knowledge components. Experiments across NarrativeQA, FairyTaleQA, and TriviaQA demonstrate a 14.81% improvement in explanation quality over the RAG-Ex baseline, with explanations correlating strongly with graph centrality measures.
GraphRAG's black-box reasoning gets a spotlight: XGRAG reveals how specific knowledge graph components influence LLM outputs, boosting explanation quality by 14.81% over standard RAG explainability methods.
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.