Millions of $\text{GeAR}$-s: Extending GraphRAG to Millions of Documents
This work addresses the limited evidence of graph-based RAG methods' general applicability for researchers in information retrieval, but it appears incremental as it adapts an existing method to a new benchmark.
The paper adapted the GeAR graph-based retrieval-augmented generation method to evaluate its performance on the SIGIR 2025 LiveRAG Challenge, aiming to test its general applicability across broader datasets.
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: $\text{GeAR}$ and explore its performance and limitations on the SIGIR 2025 LiveRAG Challenge.