LATIDIA · Ciberseguridad

Un marco multi-LLM basado en la evidencia para el modelado de dependencias de infraestructuras críticas auditables.

arXiv:2609.12360v1 Anuncio Tipo: nuevo Resumen: El conocimiento sobre infraestructura crítica se distribuye a través de evidencia heterogénea, incompleta y débilmente estructurada, lo que dificulta la construcción de modelos de dependencia automáticos.

La noticia

arXiv:2609.12360v1 Announce Type: new Abstract: Critical-infrastructure knowledge is distributed across heterogeneous, incomplete, and weakly structured evidence, making dependency models difficult to construct automatically and difficult to trust. Large language models (LLMs) can extract structured knowledge from such evidence, but direct LLM-to-graph generation risks unsupported relationships, inconsistent terminology, incorrect entity identities, and erroneous dependency endpoints. We present an evidence-first multi-LLM framework for constructing Infrastructure Knowledge Bases (IKBs) and Infrastructure Dependency Graphs (IDGs) from heterogeneous infrastructure documentation. Multiple open-weight LLMs independently extract candidate entities and dependencies from normalized evidence, after which the framework separates evidence verification, ontology grounding, entity resolution, dependency alignment, validation, fusion, and human review. Evidence support, ontology reconciliation, endpoint