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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Tianjun, Li, Haoxuan, Shen, Zhiqiang, Li, Pan, Liu, Tongliang, Zhang, Kun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913889295269888
author Yao, Tianjun
Li, Haoxuan
Shen, Zhiqiang
Li, Pan
Liu, Tongliang
Zhang, Kun
author_facet Yao, Tianjun
Li, Haoxuan
Shen, Zhiqiang
Li, Pan
Liu, Tongliang
Zhang, Kun
contents 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(LLMs) have shown strong inductive reasoning ability across various domains, but their reliability is hindered by the outdated knowledge and hallucinations.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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09645
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering
Yao, Tianjun
Li, Haoxuan
Shen, Zhiqiang
Li, Pan
Liu, Tongliang
Zhang, Kun
Computation and Language
Information Retrieval
Machine Learning
I.2.6
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.
title Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering
topic Computation and Language
Information Retrieval
Machine Learning
I.2.6
url https://arxiv.org/abs/2506.09645