analiza aiqbench
This research introduces KGFR, a novel framework that integrates Large Language Models with a structured retriever to overcome context limitations in knowledge-intensive tasks. By utilizing LLM-generated descriptions and an Asymmetric Progressive Propagation algorithm, the system achieves zero-shot generalization across unseen knowledge graphs without requiring dataset-specific fine-tuning. This approach offers a scalable solution for augmenting LLM reasoning capabilities with external structured data.
KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
arXiv:2511.04093v2 Announce Type: replace Abstract: 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.
Abstract: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.
Artificial Intelligence (cs.AI)
arXiv:2511.04093 [cs.AI]
(or arXiv:2511.04093v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2511.04093 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 240 cuvinte
Subiecte conexe
Presentation: From Retrieval to Reasoning: Building Production-Ready Agentic AI Systems with Knowledge Graphs
InfoQ · 12 sept. 2026
Presentation: Engineering AI for Creativity and Curiosity on Mobile
InfoQ · 21 iul. 2026
From Vector Search to Agentic RAG: Building an Enterprise Research Analyst with hipVS
AMD · 15 iul. 2026
Build enterprise search for agents with Amazon Bedrock Managed Knowledge Base
AWS · 16 iul. 2026