[2603.23136] HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature

Computer Science > Computation and Language arXiv:2603.23136 (cs) [Submitted on 24 Mar 2026] Title:HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature Authors:Devvrat Joshi, Islem Rekik View a PDF of the paper titled HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature, by Devvrat Joshi and Islem Rekik View PDF HTML (experimental) Abstract:Automated knowledge graph (KG) construction is essential for navigating the rapidly expanding body of scientific literature. However, existing approaches struggle to recognize long multi-word entities, often fail to generalize across domains, and typically overlook the hierarchical nature of scientific knowledge. While general-purpose large language models (LLMs) offer adaptability, they are computationally expensive and yield inconsistent accuracy on specialized tasks. As a result, current KGs are shallow and inconsistent, limiting their utility for exploration and synthesis. We propose a two-stage framework for scalable, zero-shot scientific KG construction. The first stage, Z-NERD, introduces (i) Orthogonal Semantic Decomposition (OSD), which promotes domain-agnostic entity recognition by isolating semantic "turns" in text, and (ii) a Multi-Scale TCQK attention mechanism that captures coherent multi-word entities through n-gram-aware attention heads. The second stage, HGNet, performs relation extraction with hierarchy-aware message passing...