Metraipolis › archive › dc_86cedbb2b367

Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text Translation — arXiv:2609.10923

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.10923
License (as archived): CC0-1.0
Archived: 2026-10-16T05:40:40.487Z
SHA-256 of the archived text: 0ba22c9304690eb50302874e55efe3704ad4cb0c5151ad082c00af5a80355e7b
Stable URL of this page: https://metraipolis.com/documento/dc_86cedbb2b367

How to cite

Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text Translation — arXiv:2609.10923 — arXiv (en), https://arxiv.org/abs/2609.10923 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_86cedbb2b367 (Metraipolis archive dc_86cedbb2b367, sha256 0ba22c9304690eb50302874e55efe3704ad4cb0c5151ad082c00af5a80355e7b)

BibTeX

@misc{dc86cedbb2b367,
  title = {Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text Translation — arXiv:2609.10923},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10923},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_86cedbb2b367; sha256 0ba22c9304690eb50302874e55efe3704ad4cb0c5151ad082c00af5a80355e7b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10923. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.10923 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T05:23:56.988Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).