Graph captioning improves by describing key structural motifs
Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text Translation
Computation and LanguageMachine Learning
Summary
Graphs, which show how things are connected, can be hard to describe clearly using simple lists of connections. The authors study how to write shorter, easier-to-understand descriptions by focusing on common patterns called motifs, like hubs or cycles. They introduce a method that helps computers generate captions that highlight these patterns, making the descriptions more concise while still allowing the original graph to be reconstructed. Testing on simulated graphs showed their approach keeps accuracy but makes the captions easier to read and more consistent.
What this means in practice
- •For data visualization teams: Create concise text summaries of network diagrams that highlight important structural features for clearer communication and easier comparison.
- •For knowledge graph engineers: Generate motif-focused captions for complex data graphs that preserve structure while improving interpretability without fine-tuning language models.
Tested on simulated data.
Authors
Hsiao-Ying Lu, Dongyu Liu, Kwan-Liu Ma
Abstract
Graph captions should help readers understand graph structure, rather than simply translate adjacency matrices into long textual edge lists. A useful graph caption abstracts connectivity into recognizable motifs, such as hubs, paths, cycles, cliques, and bridges, because these motifs provide compact structural units that are easier to read, compare, and recover. In this paper, we study motif-oriented graph captioning as a bidirectional graph-text translation task, where captions must both preserve enough topology for graph recovery and express the graph through concise motif-level descriptions. We show that direct prompting of GPT-5.1 often produces graph-recoverable captions by enumerating node-to-node connections, but these captions are verbose and can contain inconsistent motif interpretations. To address this gap, we introduce Structurally Speaking, a lightweight structured prompting protocol that guides translation between explicit connectivity and motif-level abstraction. Experiments on a synthetic motif-based dataset show that structured prompting produces shorter and more motif-consistent captions while maintaining comparable graph recovery. These results suggest that explicit topology-to-motif reasoning guidance can make LLM-generated graph captions more interpretable without model fine-tuning.