Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2602.02053 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915769792593920 |
|---|---|
| author | Wang, Pengyu Xu, Benfeng Zhang, Licheng Wang, Shaohan Du, Mingxuan Zhu, Chiwei Mao, Zhendong |
| author_facet | Wang, Pengyu Xu, Benfeng Zhang, Licheng Wang, Shaohan Du, Mingxuan Zhu, Chiwei Mao, Zhendong |
| contents | Graph-based Retrieval-Augmented Generation (GraphRAG) organizes external knowledge as a hierarchical graph, enabling efficient retrieval and aggregation of scattered evidence across multiple documents. However, many existing benchmarks for GraphRAG rely on short, curated passages as external knowledge, failing to adequately evaluate systems in realistic settings involving long contexts and large-scale heterogeneous documents. To bridge this gap, we introduce WildGraphBench, a benchmark designed to assess GraphRAG performance in the wild. We leverage Wikipedia's unique structure, where cohesive narratives are grounded in long and heterogeneous external reference documents, to construct a benchmark reflecting real-word scenarios. Specifically, we sample articles across 12 top-level topics, using their external references as the retrieval corpus and citation-linked statements as ground truth, resulting in 1,100 questions spanning three levels of complexity: single-fact QA, multi-fact QA, and section-level summarization. Experiments across multiple baselines reveal that current GraphRAG pipelines help on multi-fact aggregation when evidence comes from a moderate number of sources, but this aggregation paradigm may overemphasize high-level statements at the expense of fine-grained details, leading to weaker performance on summarization tasks. Project page:https://github.com/BstWPY/WildGraphBench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02053 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora Wang, Pengyu Xu, Benfeng Zhang, Licheng Wang, Shaohan Du, Mingxuan Zhu, Chiwei Mao, Zhendong Computation and Language Graph-based Retrieval-Augmented Generation (GraphRAG) organizes external knowledge as a hierarchical graph, enabling efficient retrieval and aggregation of scattered evidence across multiple documents. However, many existing benchmarks for GraphRAG rely on short, curated passages as external knowledge, failing to adequately evaluate systems in realistic settings involving long contexts and large-scale heterogeneous documents. To bridge this gap, we introduce WildGraphBench, a benchmark designed to assess GraphRAG performance in the wild. We leverage Wikipedia's unique structure, where cohesive narratives are grounded in long and heterogeneous external reference documents, to construct a benchmark reflecting real-word scenarios. Specifically, we sample articles across 12 top-level topics, using their external references as the retrieval corpus and citation-linked statements as ground truth, resulting in 1,100 questions spanning three levels of complexity: single-fact QA, multi-fact QA, and section-level summarization. Experiments across multiple baselines reveal that current GraphRAG pipelines help on multi-fact aggregation when evidence comes from a moderate number of sources, but this aggregation paradigm may overemphasize high-level statements at the expense of fine-grained details, leading to weaker performance on summarization tasks. Project page:https://github.com/BstWPY/WildGraphBench. |
| title | WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.02053 |