Communication Dans Un Congrès Année : 2025

NetBone Meets LLMs: Toward Explainable Backbone Extraction

Résumé

Despite recent progress in standardizing backbone extraction through tools like NetBone, interpreting the results remains challenging. This is especially true for non-expert users unfamiliar with the method assumptions. In this work, we extend NetBone to support interpretation through Large Language Models (LLMs). To support this, we propose a metadata-driven pipeline that automatically captures each step of the backbone extraction process, including network descriptions, method parameters, filtering settings, and structural properties. This structured metadata is used to prompt an LLM to generate contextual and method-aware explanations. We believe this extension would improve interpretability and helps users understand how method choices affect the structure and meaning of their results.

Fichier principal
Vignette du fichier
FRCCS___NetboneLLM___Ali___2025V2.pdf (198.79 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05095461 , version 1 (03-06-2025)

Licence

Identifiants

  • HAL Id : hal-05095461 , version 1

Citer

Ali Yassin, Hocine Cherifi, Hamida Seba, Olivier Togni. NetBone Meets LLMs: Toward Explainable Backbone Extraction. French Regional Conference on Complex Systems, CSS France, May 2025, Bordeaux, France. ⟨hal-05095461⟩
163 Consultations
166 Téléchargements

Partager

  • More