结构上而言：通过双向图-文本翻译实现面向模体的图描述生成
Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text Translation
- University of California, Davis（加州大学戴维斯分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出Structurally Speaking结构化提示协议，引导LLM在双向图-文本翻译中生成简洁、模体一致且可恢复的图描述，无需微调。
AI中文摘要：
图描述应帮助读者理解图结构，而非简单地将邻接矩阵翻译成冗长的文本边列表。有用的图描述应将连通性抽象为可识别的模体，如枢纽、路径、环、团和桥，因为这些模体提供了紧凑的结构单元，更易于阅读、比较和恢复。本文中，我们将面向模体的图描述生成作为双向图-文本翻译任务进行研究，其中描述必须既保留足够的拓扑信息以供图恢复，又通过简洁的模体级描述来表达图。我们表明，直接提示GPT-5.1通常通过枚举节点到节点的连接来生成可恢复图的描述，但这些描述冗长且可能包含不一致的模体解释。为解决这一差距，我们引入了Structurally Speaking，一种轻量级结构化提示协议，用于引导显式连通性与模体级抽象之间的转换。在基于合成模体的数据集上的实验表明，结构化提示生成的描述更短且模体一致性更高，同时保持可比的图恢复性能。这些结果表明，显式的拓扑到模体推理引导可以使LLM生成的图描述更具可解释性，而无需模型微调。
英文摘要：
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.
