BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering
Authors:
- Costas MavromatisCMCostas Mavromatis
- Soji AdeshinaSASoji Adeshina
- Vassilis N. IoannidisVIVassilis N. Ioannidis
- Zhen HanZHZhen Han
- Qi ZhuQZQi Zhu
- Ian RobinsonIRIan Robinson
- Bryan ThompsonBTBryan Thompson
- Huzefa RangwalaHRHuzefa Rangwala
- George KarypisGKGeorge Karypis
Preprint
Abstract
Knowledge graph question answering (KGQA) presents significant challenges due to the structural and semantic variations across input graphs. Existing works rely on Large Language Model (LLM) agents for graph traversal and retrieval; an approach that is sensitive to traversal initialization, as it is prone to entity linking errors and may not generalize well to custom ("bring-your-own") KGs. We introduce BYOKG-RAG, a framework that enhances KGQA by synergistically combining LLMs with specialized graph retrieval tools. In BYOKG-RAG, LLMs generate critical graph artifacts (question entities, candidate answers, reasoning paths, and OpenCypher queries), and graph tools link these artifacts to the KG and retrieve relevant graph context. The retrieved context enables the LLM to iteratively refine its graph linking and retrieval, before final answer generation. By retrieving context from different graph tools, BYOKG-RAG offers a more general and robust solution for QA over custom KGs. Through experiments on five benchmarks spanning diverse KG types, we demonstrate that BYOKG-RAG outperforms the second-best graph retrieval method by 4.5% points while showing better generalization to custom KGs. BYOKG-RAG framework is open-sourced at https://github.com/awslabs/graphrag-toolkit.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational PathsProceedings of the AAAI Conference on Artificial Intelligence, 2026
- Graph Retrieval-Augmented Generation: A SurveyACM Transactions on Information Systems, 2025
- The Faiss LibraryIEEE Transactions on Big Data, 2025
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation2024
- Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA2024
- KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models2023
- End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs2021
- TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph2021
- Efficient One-Pass End-to-End Entity Linking for Questions2020
- Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases2020