华侨大学学报（自然科学版）2026，Vol.47Issue(2)：202-212,11.DOI:10.11830/ISSN.1000-5013.202511013
基于反思型证据增强的知识图谱可解释问答框架
Reflective Evidence-Enhanced Explainable Knowledge Graph Question Answering Framework
摘要
Abstract
To address the issue that current large language models exhibit strong multi-hop reasoning capabili-ties but lack of interpretability in knowledge graph question-answering tasks,a reflective evidence-enhanced explainable knowledge graph question answering(ReE-KGQA)framework is proposed.First,candidate se-mantic paths are generated using large language models,and a comprehensive scoring and verification strategy integrating immediate semantic relevance with graph structural connectivity is employed to select optimal rea-soning paths as explainable evidence.Then,a joint optimization fine-tuning strategy for answer generation and path rationality is designed to simultaneously enhance question answering performance and reasoning interpret-ability.Finally,extensive evaluations are conducted on three commonly used benchmark datasets.Experimen-tal results show that the ReE-KGQA framework outperforms existing mainstream methods across key metrics including Hits@1,F1-score,and accuracy,achieving an average improvement of approximately 9％.More-over,the generated reasoning paths exhibit favorable semantic readability.The proposed framework effectively improves both the accuracy and reliability of the answers while enhancing the interpretability of knowledge graph question answering.关键词
知识图谱问答/可解释推理/反思型证据/大语言模型Key words
knowledge graph question answering/explainable reasoning/reflective evidence/large language model分类
信息技术与安全科学引用本文复制引用
林海斌,康泽民,洪鸣,王华珍..基于反思型证据增强的知识图谱可解释问答框架[J].华侨大学学报（自然科学版）,2026,47(2):202-212,11.基金项目
华侨大学中央高校基本科研业务费资助项目(2024HQYJ01) （2024HQYJ01）
