Jul 2026
HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Document
Question answering (QA) over complex documents requires models to retrieve and integrate evidence distributed across distant document regions and modalities. Multimodal GraphRAG provides a promising direction by organizing document evidence with graph structures. However, existing methods often suffer from unreliable c...
Xingbo He, Yi-Li Wang, Wenqi Fan et al.
· arXiv.org · 1 citation