KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
This addresses the challenge of scalable and generalizable knowledge graph question answering for applications requiring reasoning over large or unseen graphs, representing an incremental improvement over existing methods.
The authors tackled the problem of knowledge-intensive question answering by proposing LLM-KGFR, a collaborative framework that combines an LLM with a structured retriever to enable zero-shot generalization to unseen knowledge graphs while handling large graphs efficiently. The result is a system that achieves strong performance with scalability and generalization, providing a practical solution for KG-augmented reasoning.
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.