Millions of GeAR-s: Extending GraphRAG to Millions of Documents
On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Abstract (arXiv)
Recent studies have explored graph-based approaches to retrieval-augmented generation, leveraging structured or semi-structured information -- such as entities and their relations extracted from documents -- to enhance retrieval. However, these methods are typically designed to address specific tasks, such as multi-hop question answering and query-focused summarisation, and therefore, there is limited evidence of their general applicability across broader datasets. In this paper, we aim to adapt a state-of-the-art graph-based RAG solution: GeAR and explore its performance and limitations on the SIGIR 2025 LiveRAG Challenge.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 0 of its 6 references that are in the map. First posted on arXiv 23 Jul 2025.
Builds on
0 of 6 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough
- 2025Query-Centric Graph Retrieval Augmented Generation
- 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes
- 2024GeAR: Graph-enhanced Agent for Retrieval-augmented Generation
- 2025Clue-RAG: Towards Accurate and Cost-Efficient Graph-based RAG via Multi-Partite Graph and Query-Driven Iterative Retrieval
- 2025RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
- 2024Graph Retrieval-Augmented Generation: A Survey
- 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG