[2512.21106] Semantic Refinement with LLMs for Graph Representations

Computer Science > Computation and Language arXiv:2512.21106 (cs) [Submitted on 24 Dec 2025 (v1), last revised 1 Apr 2026 (this version, v2)] Title:Semantic Refinement with LLMs for Graph Representations Authors:Safal Thapaliya, Zehong Wang, Jiazheng Li, Ziming Li, Yanfang Ye, Chuxu Zhang View a PDF of the paper titled Semantic Refinement with LLMs for Graph Representations, by Safal Thapaliya and 5 other authors View PDF HTML (experimental) Abstract:Graph-structured data exhibit substantial heterogeneity in where their predictive signals originate: in some domains, node-level semantics dominate, while in others, structural patterns play a central role. This structure-semantics heterogeneity implies that no graph learning model with a fixed inductive bias can generalize optimally across diverse graph domains. However, most existing methods address this challenge from the model side by incrementally injecting new inductive biases, which remains fundamentally limited given the open-ended diversity of real-world graphs. In this work, we take a data-centric perspective and treat node semantics as a task-adaptive variable. We propose a Graph-Exemplar-guided Semantic Refinement (GES) framework for graph representation learning which -- unlike existing LLM-enhanced methods that generate node descriptions without graph context -- leverages structurally and semantically similar nodes from the graph itself to guide semantic refinement. Specifically, a GNN is first trained to produce...