Millions of $\text{GeAR}$-s: Extending GraphRAG to Millions of Documents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912498254348288 |
|---|---|
| author | Shen, Zhili Diao, Chenxin Merita, Pascual Vougiouklis, Pavlos Pan, Jeff Z. |
| author_facet | Shen, Zhili Diao, Chenxin Merita, Pascual Vougiouklis, Pavlos Pan, Jeff Z. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_17399 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Millions of $\text{GeAR}$-s: Extending GraphRAG to Millions of Documents Shen, Zhili Diao, Chenxin Merita, Pascual Vougiouklis, Pavlos Pan, Jeff Z. Computation and Language Artificial Intelligence Information Retrieval 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. |
| title | Millions of $\text{GeAR}$-s: Extending GraphRAG to Millions of Documents |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2507.17399 |