PanoramaRAG: Enabling Consistent Global Topic Awareness in Graph-Based RAG

ACL ARR 2026 January Submission6001 Authors

Keywords: Artificial Intelligence, Information Retrieval, Retrieval-Augmented Generation

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.

Paper Type: Long

Research Area: Information Extraction and Retrieval

Research Area Keywords: Computation and Language, Retrieval-Augmented Generation, Information Retrieval, Artificial Intelligence, Index Construction

Languages Studied: English, Chinese

Submission Number: 6001