PRISM: Proof-Carrying Artifact Generation through LLM x MDE Synergy and Stratified Constraints
This addresses the need for automated, verifiable artifact generation in domains like automotive software and legal compliance, though it appears incremental as it builds on existing LLM and MDE techniques.
PRISM tackles the problem of generating regulator-ready artifacts with machine-checkable evidence for safety- and compliance-critical domains by unifying Large Language Models with Model-Driven Engineering, resulting in structurally valid, auditable artifacts that substantially reduce manual remediation effort.
PRISM unifies Large Language Models with Model-Driven Engineering to generate regulator-ready artifacts and machine-checkable evidence for safety- and compliance-critical domains. PRISM integrates three pillars: a Unified Meta-Model (UMM) reconciles heterogeneous schemas and regulatory text into a single semantic space; an Integrated Constraint Model (ICM) compiles structural and semantic requirements into enforcement artifacts including generation-time automata (GBNF, DFA) and post-generation validators (e.g., SHACL, SMT); and Constraint-Guided Verifiable Generation (CVG) applies these through two-layer enforcement - structural constraints drive prefix-safe decoding while semantic/logical validation produces machine-checkable certificates. When violations occur, PRISM performs audit-guided repair and records generation traces for compliance review. We evaluate PRISM in automotive software engineering (AUTOSAR) and cross-border legal jurisdiction (Brussels I bis). PRISM produces structurally valid, auditable artifacts that integrate with existing tooling and substantially reduce manual remediation effort, providing a practical path toward automated artifact generation with built-in assurance.