SuperRAG: Beyond RAG with Layout-Aware Graph Modeling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929745654972416 |
|---|---|
| author | Yang, Jeff Vu, Duy-Khanh Nguyen, Minh-Tien Nguyen, Xuan-Quang Nguyen, Linh Le, Hung |
| author_facet | Yang, Jeff Vu, Duy-Khanh Nguyen, Minh-Tien Nguyen, Xuan-Quang Nguyen, Linh Le, Hung |
| contents | This paper introduces layout-aware graph modeling for multimodal RAG. Different from traditional RAG methods that mostly deal with flat text chunks, the proposed method takes into account the relationship of multimodalities by using a graph structure. To do that, a graph modeling structure is defined based on document layout parsing. The structure of an input document is retained with the connection of text chunks, tables, and figures. This representation allows the method to handle complex questions that require information from multimodalities. To confirm the efficiency of the graph modeling, a flexible RAG pipeline is developed using robust components. Experimental results on four benchmark test sets confirm the contribution of the layout-aware modeling for performance improvement of the RAG pipeline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04790 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SuperRAG: Beyond RAG with Layout-Aware Graph Modeling Yang, Jeff Vu, Duy-Khanh Nguyen, Minh-Tien Nguyen, Xuan-Quang Nguyen, Linh Le, Hung Computation and Language Artificial Intelligence This paper introduces layout-aware graph modeling for multimodal RAG. Different from traditional RAG methods that mostly deal with flat text chunks, the proposed method takes into account the relationship of multimodalities by using a graph structure. To do that, a graph modeling structure is defined based on document layout parsing. The structure of an input document is retained with the connection of text chunks, tables, and figures. This representation allows the method to handle complex questions that require information from multimodalities. To confirm the efficiency of the graph modeling, a flexible RAG pipeline is developed using robust components. Experimental results on four benchmark test sets confirm the contribution of the layout-aware modeling for performance improvement of the RAG pipeline. |
| title | SuperRAG: Beyond RAG with Layout-Aware Graph Modeling |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.04790 |