An Evidence-First Multi-LLM Framework for Auditable Critical-Infrastructure Dependency Modeling
Evidence-first multi-LLM framework builds auditable critical-infrastructure dependency graphs while preserving provenance and unresolved cases.
The framework constructs Infrastructure Knowledge Bases and Infrastructure Dependency Graphs from heterogeneous infrastructure documentation using multiple open-weight LLMs that independently extract candidate entities and dependencies from normalized evidence. It separates evidence verification, ontology grounding, entity resolution, dependency alignment, validation, fusion, and human review, projecting the validated IKB deterministically into the IDG without new LLM-generated knowledge. Evaluation across nine infrastructure projects shows entity recovery achieves substantially higher recall than full dependency recovery, and cross-model overlap is much lower for dependencies than entities, indicating models often produce non-overlapping candidate assertions rather than stable consensus.
- Multiple open-weight LLMs independently extract candidate entities and dependencies from evidence
- Pipeline separates verification, ontology grounding, resolution, validation, fusion, and human review
- Validated IKB projected deterministically to IDG without introducing new LLM knowledge
- Entity recovery recall exceeds dependency recovery; cross-model dependency overlap is low across nine projects
From the original article
1 min read at arxiv.orgCritical-infrastructure knowledge is distributed across heterogeneous, incomplete, and weakly structured evidence, making dependency models difficult to construct automatically and difficult to trust.
By Nurjahan · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.