Metraipolis › archive › dc_cb89eb3ad978

Language-encoded network topology enables large language models to reason about complex networks — arXiv:2609.03229

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03229
License (as archived)
CC0-1.0
Archived
2026-10-17T02:07:49.561Z
SHA-256 of the archived text
863e2cf4c867ffe94ff3d80db59a13eaad26b3437d217937a31b534b2e3a2731
Stable URL of this page
https://metraipolis.com/documento/dc_cb89eb3ad978

How to cite

Language-encoded network topology enables large language models to reason about complex networks — arXiv:2609.03229 — arXiv (en), https://arxiv.org/abs/2609.03229 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb89eb3ad978 (Metraipolis archive dc_cb89eb3ad978, sha256 863e2cf4c867ffe94ff3d80db59a13eaad26b3437d217937a31b534b2e3a2731)
BibTeX
@misc{dccb89eb3ad978,
  title = {Language-encoded network topology enables large language models to reason about complex networks — arXiv:2609.03229},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03229},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb89eb3ad978; sha256 863e2cf4c867ffe94ff3d80db59a13eaad26b3437d217937a31b534b2e3a2731},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03229. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Networks describe systems in biology and beyond, from protein interactions and social relationships to power grids and citation records. Reasoning about such systems requires understanding their structure: which elements are central, which connections bridge separate communities, and how it changes when elements are removed. Although large language models (LLMs) excel at natural language, they struggle with such questions when networks are given as edge lists, sentences or measurement tables, because their structural meaning must be inferred. Here we introduce BioGlyph, which compiles network topology into an interpretable and transferable language of structural roles. BioGlyph combines graph partitioning and structural measurements to identify roles such as hubs, community cores and cross-community connectors, and fixed rules to translate them into a universal vocabulary. The representation describes each element through its structural role, supporting evidence and semantic consequences, leaving both the network and the LLM unchanged. Across twenty networks spanning five domains, BioGlyph substantially improves open LLMs' ability to answer structural reasoning questions, outperforming edge-based, numerical and learned representations by up to 26 percentage points in system accuracy. Ablations show that the gain comes from explicitly encoding structural roles in semantically interpretable terms. The gain is more prominent in dense, community-structured networks and diminishes in sparse networks whose topology is more readily inferred from text. In a budding-yeast protein-interaction network, BioGlyph exposes biological organization: cross-community connectors are enriched for essential genes, whereas peripheral proteins are depleted. BioGlyph thus provides an interpretable representation for both language models and scientists to reason about network structure.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.03229 — 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 2026-10-17T01:47:25.529Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).