QA-GraphRAG: Query-Adaptive Plug-and-Play Retrieval Integration for Graph-based Retrieval-Augmented Generation
Proceedings of the VLDB Endowment · 01.05.2026 · 19 (9) · 2224-2233
DOI: 10.14778/3819518.3819546 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 19.08.2026. Verfasst von Zeang Sheng und 6 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben.
Abstract (Originalsprache)
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet they often suffer from hallucinations and lack up-to-date knowledge. Retrieval-Augmented Generation (RAG) addresses these limitations by grounding LLMs in external knowledge. While vector-based RAG is effective for simple queries, it struggles with complex queries that require multi-hop reasoning. Graph-based RAG frameworks have emerged to solve this by constructing knowledge graphs that capture global relationships and enable multi-hop reasoning. However, these graph-based approaches frequently underperform on simple fact-based queries compared to their vector-based counterparts, as they may lose detailed entity information. In this paper, we conduct dataset-level and framework-level analysis targeting graph-based RAG approaches. We find that existing QA benchmark datasets can be split to "Local" and "Global" queries that have different properties; and different RAG frameworks perform differently on these two kinds of queries. Concretely, existing graph-based RAG frameworks, including recent dual-branch ones, cannot consistently outperform vector-based RAG on "Local" queries. We attribute this phenomenon to the fact that graph-based RAG often employs a fixed retrieval strategy, leading to redundant information retrieval and unnecessary cost for simple queries. Based on the analysis, we propose QA-GraphRAG, a new query-adaptive plug-and-play retrieval integration for graph-based RAG frameworks. QA-GraphRAG incorporates a pre-trained router that predicts the optimal knowledge hierarchy from which to start retrieval based on the characteristics of the input query. Extensive experiments on KGQA datasets and GraphRAG-Bench demonstrate that equipping existing graph-based RAG frameworks with our QA-GraphRAG leads to substantial performance improvements.
Zitieren
APA
Sheng, Z., Sun, R., Xu, J., Luo, H., Chen, P., Zhang, W., & Cui, B. (2026). QA-GraphRAG: Query-Adaptive Plug-and-Play Retrieval Integration for Graph-based Retrieval-Augmented Generation. Proceedings of the VLDB Endowment, 19(9), 2224-2233. https://doi.org/10.14778/3819518.3819546
Vancouver
Sheng Z, Sun R, Xu J, Luo H, Chen P, Zhang W, et al. QA-GraphRAG: Query-Adaptive Plug-and-Play Retrieval Integration for Graph-based Retrieval-Augmented Generation. Proceedings of the VLDB Endowment. 2026;19(9):2224-2233. doi:10.14778/3819518.3819546
BibTeX
@article{Sheng2026,
author = {Sheng, Zeang and Sun, Ruihong and Xu, Jiahao and Luo, Hanmei and Chen, Peng and Zhang, Wentao and Cui, Bin},
title = {QA-GraphRAG: Query-Adaptive Plug-and-Play Retrieval Integration for Graph-based Retrieval-Augmented Generation},
journal = {Proceedings of the VLDB Endowment},
year = {2026},
volume = {19},
number = {9},
pages = {2224--2233},
doi = {10.14778/3819518.3819546}
}
EUVIMED