DiagramBank is a large-scale curated dataset of 89,422 schematic diagrams from scientific papers with rich metadata to support multimodal retrieval and exemplar-driven figure generation.
ISBN 978-1-68558- 244-9
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
DiagramRAG is a retrieval-augmented framework that represents diagrams as knowledge graphs, synthesizes sketch variants, trains an embedding model for structure-aware retrieval, and uses retrieved references to guide sketch-based scientific diagram generation.
Large language models generate acceptable ER diagrams from simple requirements but show declining reliability, inconsistencies, and constraint failures as scenario complexity increases.
citing papers explorer
-
DiagramRAG: A Lightweight Framework to Retrieve Scientific Diagram for Figure Generation
DiagramRAG is a retrieval-augmented framework that represents diagrams as knowledge graphs, synthesizes sketch variants, trains an embedding model for structure-aware retrieval, and uses retrieved references to guide sketch-based scientific diagram generation.
-
On the Limitations of Large Language Models for Conceptual Database Modeling
Large language models generate acceptable ER diagrams from simple requirements but show declining reliability, inconsistencies, and constraint failures as scenario complexity increases.