Saved in:
Bibliographic Details
Main Authors: Cui, Yuanning, Sun, Zequn, Hu, Wei, Fu, Zhangjie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.04093
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909889784184832
author Cui, Yuanning
Sun, Zequn
Hu, Wei
Fu, Zhangjie
author_facet Cui, Yuanning
Sun, Zequn
Hu, Wei
Fu, Zhangjie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04093
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
Cui, Yuanning
Sun, Zequn
Hu, Wei
Fu, Zhangjie
Artificial Intelligence
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.
title KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
topic Artificial Intelligence
url https://arxiv.org/abs/2511.04093