Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering

TL;DR

This paper introduces RAPL, a novel graph retrieval framework for knowledge-graph question answering that improves accuracy, interpretability, and generalization by combining a two-stage labeling strategy, graph transformation, and path-based reasoning.

Contribution

RAPL presents a new, model-agnostic approach to graph retrieval in KGQA, enhancing representational capacity and reasoning ability, and outperforming existing methods in accuracy and generalization.

Findings

RAPL outperforms state-of-the-art methods by 2.66%-20.34%.

It reduces the performance gap between smaller and larger LLMs.

It demonstrates strong generalizability across datasets.

Abstract

Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains, but their reliability is hindered by the outdated knowledge and hallucinations. Retrieval-Augmented Generation mitigates these issues by grounding LLMs with external knowledge; however, most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning. Knowledge graphs, which represent facts as relational triples, offer a more structured and compact alternative. Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering (KGQA), with a significant proportion adopting the retrieve-then-reasoning paradigm. In this framework, graph-based retrievers have demonstrated strong empirical performance, yet they still face challenges in generalization ability. In this work, we propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA. RAPL addresses these limitations through three aspects: (1) a two-stage labeling strategy that combines heuristic signals with parametric models to provide causally grounded supervision; (2) a model-agnostic graph transformation approach to capture both intra- and inter-triple interactions, thereby enhancing representational capacity; and (3) a path-based reasoning strategy that facilitates learning from the injected rational knowledge, and supports downstream reasoner through structured inputs. Empirically, RAPL outperforms state-of-the-art methods by $2.66\%-20.34\%$, and significantly reduces the performance gap between smaller and more powerful LLM-based reasoners, as well as the gap under cross-dataset settings, highlighting its superior retrieval capability and generalizability. Codes are available at: https://github.com/tianyao-aka/RAPL.