arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.04093cs.AI
收藏

KGFR:面向通用知识图谱问答的基础检索器

KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering

School of Computer Science, Nanjing University of Information Science and Technology(南京信息工程大学计算机科学学院);State Key Laboratory for Novel Software Technology, Nanjing University(南京大学软件新技术国家重点实验室);National Institute of Healthcare Data Science, Nanjing University(南京大学健康数据科学国家研究院);Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology(南京信息工程大学教育部长江数字取证工程研究中心)

Yuanning Cui, Zequn Sun, Wei Hu, Zhangjie Fu

AI总结:

本文提出LLM-KGFR协作框架,通过KGFR结合LLM与结构化检索能力,实现对未见过KG的零样本泛化,采用APP高效处理大型图谱,形成可控推理循环,在KG问答任务中兼具高性能、可扩展性与泛化性。

摘要:

大语言模型(LLM)擅长推理,但受限于有限的上下文和参数化知识,在处理知识密集型问题时表现不佳。现有依赖微调LLM或GNN检索器的方法受限于特定数据集的微调,且在大型或未见过的图谱上的可扩展性不足。本文提出LLM-KGFR协作框架,其中LLM与结构化检索器——知识图谱基础检索器(KGFR)协同工作。KGFR利用LLM生成的描述对关系进行编码,并根据实体在问题中的角色初始化实体,从而实现对未见过的知识图谱(KG)的零样本泛化。为高效处理大型图谱,它采用非对称渐进传播(APP),这是一种逐步扩展的方法,可选择性限制高度节点,同时保留信息路径。通过节点、边和路径级接口,LLM迭代请求候选答案、支撑事实和推理路径,形成可控的推理循环。实验表明,LLM-KGFR在保持可扩展性和泛化性的同时取得了优异性能,为增强KG的推理提供了实用解决方案。

英文摘要:

Large language models (LLMs) excel at reasoning but struggle with knowledge-intensive questions due to limited context and parametric knowledge. However, existing methods that rely on finetuned LLMs or GNN retrievers are limited by dataset-specific tuning and scalability on large or unseen graphs. We propose the LLM-KGFR collaborative framework, where an LLM works with a structured retriever, the Knowledge Graph Foundation Retriever (KGFR). KGFR encodes relations using LLM-generated descriptions and initializes entities based on their roles in the question, enabling zero-shot generalization to unseen KGs. To handle large graphs efficiently, it employs Asymmetric Progressive Propagation (APP)- a stepwise expansion that selectively limits high-degree nodes while retaining informative paths. Through node-, edge-, and path-level interfaces, the LLM iteratively requests candidate answers, supporting facts, and reasoning paths, forming a controllable reasoning loop. Experiments demonstrate that LLM-KGFR achieves strong performance while maintaining scalability and generalization, providing a practical solution for KG-augmented reasoning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑