基于反思型证据增强的知识图谱可解释问答框架OA

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.