Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs
用于知识图谱中演绎推理的可控逻辑假设生成
机构 * Department of Computer Science and Engineering(计算机科学与工程系) ; The Hong Kong University of Science and Technology(香港理工大学) ; Beihang University(北航) ; Key Lab of Education Blockchain and Intelligent Technology(教育区块链与智能技术重点实验室) ; Guangxi Normal University(广西师范大学)
专题命中 医学数据与评测 :diagnosis(abstract)
AI总结 本文提出CtrlHGen框架,通过监督学习和强化学习解决知识图谱中假设生成的可控性问题,提升假设生成的准确性和实用性。
Comments Accepted by ICLR2026