Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering
本体引导的反向思维使大语言模型在知识图谱问答中更强
机构 * Harbin Institute of Technology(哈尔滨工业大学) ; Beijing University of Posts and Telecommunications(北京邮电大学) ; Joint Laboratory of HIT and iFLYTEK(哈工大与科大讯飞联合实验室) ; University of Science and Technology of China(中国科学技术大学) ; Pengcheng Laboratory(鹏城实验室)
专题命中 其他推理 :reasoning(abstract);分类 cs.CL、cs.AI
AI总结 本文提出Ontology-Guided Reverse Thinking框架,通过反向推理构建路径,提升大语言模型在知识图谱问答中的表现,实验表明其在WebQSP和CWQ数据集上达到最佳性能。
Comments We now public our source codes