Language-encoded network topology enables large language models to reason about complex networks

• URL: http://arxiv.org/abs/2609.03229v1
• Date: Thu, 03 Sep 2026 00:04:31 GMT
• Title: Language-encoded network topology enables large language models to reason about complex networks
• Abstract summary: We introduce BioGlyph, which compiles network topology into an interpretable and transferable language of structural roles.<n>Across twenty networks spanning five domains, BioGlyph substantially improves open language models' ability to answer structural reasoning questions.
• Score: 28.6220976244699
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Unifying Graph Neural Networks Through a Common Layer Equation [75.88127999406392]
  We introduce a common layer equation that represents covered architectures through seven components.<n>The central factorization separates where information moves, encoded by the propagation bank, from what moves, encoded by the message maps.<n>We make this unification explicit and checkable through worked reductions of canonical layers and component assignments.
  arXiv  Detail & Related papers  (2026-08-17T04:37:59Z)
• Semantic Loss Functions for Neuro-Symbolic Structured Prediction [74.18322585177832]
  We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training. It is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby. It can be combined with both discriminative and generative neural models.
  arXiv  Detail & Related papers  (2024-05-12T22:18:25Z)
• Topological properties and organizing principles of semantic networks [3.8462776107938317]
  We study the properties of semantic networks from ConceptNet, defined by 7 semantic relations from 11 different languages. We find that semantic networks have universal basic properties: they are sparse, highly clustered, and many exhibit power-law degree distributions. In some networks the connections are similarity-based, while in others the connections are more complementarity-based.
  arXiv  Detail & Related papers  (2023-04-24T11:12:21Z)
• LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model [96.889634747943]
  Universally modeling all typical information extraction tasks (UIE) with one generative language model (GLM) has revealed great potential. We propose a novel structure-aware GLM, fully unleashing the power of syntactic knowledge for UIE. Over 12 IE benchmarks across 7 tasks our system shows significant improvements over the baseline UIE system.
  arXiv  Detail & Related papers  (2023-04-13T04:01:14Z)
• How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding [56.222097640468306]
  We provide mechanistic understanding of how transformers learn "semantic structure" We show, through a combination of mathematical analysis and experiments on Wikipedia data, that the embedding layer and the self-attention layer encode the topical structure.
  arXiv  Detail & Related papers  (2023-03-07T21:42:17Z)
• TeKo: Text-Rich Graph Neural Networks with External Knowledge [75.91477450060808]
  We propose a novel text-rich graph neural network with external knowledge (TeKo) We first present a flexible heterogeneous semantic network that incorporates high-quality entities. We then introduce two types of external knowledge, that is, structured triplets and unstructured entity description.
  arXiv  Detail & Related papers  (2022-06-15T02:33:10Z)
• Latent Topology Induction for Understanding Contextualized Representations [84.7918739062235]
  We study the representation space of contextualized embeddings and gain insight into the hidden topology of large language models. We show there exists a network of latent states that summarize linguistic properties of contextualized representations.
  arXiv  Detail & Related papers  (2022-06-03T11:22:48Z)
• The Hierarchical Organization of Syntax [0.0]
  We analyze the hierarchical organization of historical syntactic networks to understand how syntax evolves over time. We created these networks from a corpus of German texts from the 11th to 17th centuries. We named these syntactic structures "syntactic communicative hierarchies"
  arXiv  Detail & Related papers  (2021-11-27T00:47:54Z)
• Compositional Networks Enable Systematic Generalization for Grounded Language Understanding [21.481360281719006]
  Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abilities when presented with novel sentences, systematic variation uncovers the limitations in the language-understanding abilities of networks. We demonstrate that these limitations can be overcome by addressing the generalization challenges in the gSCAN dataset.
  arXiv  Detail & Related papers  (2020-08-06T16:17:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.