STEM: Structure-Tracing Evidence Mining for Knowledge Graphs-Driven Retrieval-Augmented Generation

TL;DR

STEM introduces a novel graph search framework for knowledge graph question answering, improving reasoning accuracy and evidence retrieval by leveraging global structural information and schema-guided decomposition.

Contribution

The paper proposes STEM, a new framework that redefines multi-hop reasoning as a schema-guided graph search, incorporating a Triple-GNN for global structural guidance in KGQA.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Significantly improves reasoning accuracy and evidence completeness.

Effectively integrates global structural information into KG reasoning.

Abstract

Knowledge Graph-based Question Answering (KGQA) plays a pivotal role in complex reasoning tasks but remains constrained by two persistent challenges: the structural heterogeneity of Knowledge Graphs(KGs) often leads to semantic mismatch during retrieval, while existing reasoning path retrieval methods lack a global structural perspective. To address these issues, we propose Structure-Tracing Evidence Mining (STEM), a novel framework that reframes multi-hop reasoning as a schema-guided graph search task. First, we design a Semantic-to-Structural Projection pipeline that leverages KG structural priors to decompose queries into atomic relational assertions and construct an adaptive query schema graph. Subsequently, we execute globally-aware node anchoring and subgraph retrieval to obtain the final evidence reasoning graph from KG. To more effectively integrate global structural information during the graph construction process, we design a Triple-Dependent GNN (Triple-GNN) to generate a Global Guidance Subgraph (Guidance Graph) that guides the construction. STEM significantly improves both the accuracy and evidence completeness of multi-hop reasoning graph retrieval, and achieves State-of-the-Art performance on multiple multi-hop benchmarks.