@inproceedings{deng-etal-2026-panoramarag,
    title = "{P}anorama{RAG}: Enabling Consistent Global Topic Awareness in Graph-Based {RAG}",
    author = "Deng, Ding  and
      Li, Xiang  and
      Zhang, Yaqing  and
      Li, Meng  and
      Wang, Xiting",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1998/",
    pages = "40205--40217",
    ISBN = "979-8-89176-395-1",
    abstract = "Graph-based Retrieval-Augmented Generation (RAG), which models relationships between fine-grained semantic units as a graph, effectively facilitates multi-hop reasoning to enhance large language model generation. However, its design focuses on local relationships, resulting in suboptimal performance for tasks that require global context, and the separation of query refinement from indexing limits the system{'}s ability to capture high-level implicit relationships within the graph. This paper proposes a **Panorama**-guided **RAG** paradigm (PanoramaRAG) that integrates a light yet comprehensive ``panorama'' of the corpus to guide all stages of the retrieval process. This hub bridges the knowledge graph, language models, and queries in a computationally efficient manner, applicable to both open-source and closed-source models. Experimental results demonstrate that our method exhibits strong performance across five datasets and a variety of tasks."
}