Didact: A Cross-Domain Capability Discovery System for Defence

2026-06-05

AI Summary

This study addresses the challenges of fragmented, heterogeneous, and siloed information in defense policy formulation, which hinder efficient capability discovery and auditability. To tackle these issues, the authors develop a knowledge graph prototype integrating publicly available Australian defense reports, policy documents, and scientific publications. The system supports natural language interaction aligned with policy workflows and enables cross-domain capability discovery through a hybrid retrieval-augmented generation (RAG) approach. A novel “Evidence Rail” visualization mechanism is introduced to dynamically trace evidence provenance and interrelationships, substantially enhancing explainability and audit capacity. Evaluated in an Australian defense context, the system demonstrates strong performance in output quality and computational efficiency, with successful validation across industry, government, and academia, and shows promise for transferability to other domains characterized by knowledge fragmentation.

Abstract

Policymakers in defence and defence-aligned sectors must monitor rapidly evolving research alongside sector priorities relevant to operational and strategic needs. In practice, these sources are fragmented across heterogeneous formats, disjoint repositories, and siloed update streams, making capability discovery slow and difficult to audit. We present Didact, a prototype that integrates publicly available defence reports and policy documents from Australia with a purpose-built knowledge graph derived from Australian research publications. Didact provides natural language conversations for policy-oriented workflows, and leverages a composite retrieval-augmented generation (RAG) pipeline. A key feature of Didact is an interactive Evidence Rail that visualises retrieved evidence and source relationships. Our evaluation of the output quality and runtime of Didact highlights its utility. While Didact has been co-developed as an academia-industry project for the Australian context, it is adaptable to other domains where knowledge is similarly fragmented. A demonstration video is available here:

Problem

• capability discovery
• defence policy
• knowledge fragmentation
• heterogeneous data sources
• strategic research monitoring

Innovation

• retrieval-augmented generation
• knowledge graph
• capability discovery
• evidence visualization
• cross-domain integration