山西大学学报（自然科学版）2026，Vol.49Issue(4)：535-546,12.DOI:10.13451/j.sxu.ns.2025120
融合大语言模型与动态反馈机制的鸟类知识图谱补全方法
Research on Bird Knowledge Graph Completion Integrating Large Language Models and Dynamic Feedback Mechanisms
摘要
Abstract
Knowledge graphs have been widely used to transform fragmented information into structured and inferable relations,thereby supporting research on bird migration,conservation,and biodiversity.However,due to the high specialization and complexi-ty of avian knowledge,as well as the diversity of entity relations,existing bird-domain knowledge graphs have remained limited in coverage and exhibited shallow relation extraction.To address these limitations,a bird-domain knowledge graph completion frame-work was proposed by integrating large language models with fine-tuning and a dynamic feedback mechanism.The framework was designed to enhance the understanding and reasoning of fine-grained avian knowledge for more efficient graph completion.Specifi-cally,the Qwen model was fine-tuned using a domain-oriented instruction set to improve its specialized inference capability,and a dynamic feedback mechanism was incorporated to further strengthen reasoning and information extraction.Under relaxed evaluation settings,the proposed method achieved a Hits@1 of 63.0%,representing a 50.76%improvement over ChatGPT.With feedback en-hancement,the performance increased to 95.3%,surpassing DeepSeek by 3.1%.The correct model outputs were iteratively integrat-ed back into the graph,forming a closed-loop process of fine-tuning,completion,feedback,and expansion,which continuously strengthened self-learning and vertical-domain completion ability.关键词
领域知识图谱/指令微调/知识推理Key words
domain-specific knowledge graph/instruction tuning/knowledge reasoning分类
信息技术与安全科学引用本文复制引用
蒋永佳,耿生玲,贾泽宇,李升宏..融合大语言模型与动态反馈机制的鸟类知识图谱补全方法[J].山西大学学报（自然科学版）,2026,49(4):535-546,12.基金项目
中央引导地方科技发展专项(2024ZY050) （2024ZY050）
国家自然科学基金(6246070542) （6246070542）
青海师范大学中青年科研基金资助项目(2023QZR016) （2023QZR016）
