Optimizing open-domain question answering with graph-based retrieval augmented generation

In this work, we benchmark various graph-based retrieval-augmented generation (RAG) systems across a broad spectrum of query types, including OLTP-style (fact-based) and OLAP-style (thematic) queries, to address the complex demands of open-domain question answering (QA). Traditional RAG methods often fall short in handling nuanced, multi-document synthesis tasks. By structuring knowledge as graphs, we can facilitate the retrieval of context that captures greater semantic depth and enhances language model operations. We explore graph-based RAG methodologies and introduce TREX, a novel, cost-effective alternative that combines graph-based and vector-based retrieval techniques. Our benchmarking across four diverse datasets highlights the strengths of different RAG methodologies, demonstrates TREX's ability to handle multiple open-domain QA types, and reveals the limitations of current evaluation methods.In a real-world technical support case study, we demonstrate how TREX solutions can surpass conventional vector-based RAG in efficiently synthesizing data from heterogeneous sources. Our findings underscore the potential of augmenting large language models with advanced retrieval and orchestration capabilities, advancing scalable, graph-based AI solutions.

@article{cahoon2025_2503.02922,
  title={ Optimizing open-domain question answering with graph-based retrieval augmented generation },
  author={ Joyce Cahoon and Prerna Singh and Nick Litombe and Jonathan Larson and Ha Trinh and Yiwen Zhu and Andreas Mueller and Fotis Psallidas and Carlo Curino },
  journal={arXiv preprint arXiv:2503.02922},
  year={ 2025 }
}