Compliance-by-Construction Argument Graphs: Using Generative AI to Produce Evidence-Linked Formal Arguments for Certification-Grade Accountability

TL;DR

This paper introduces a formal architecture combining Generative AI with structured argument graphs to enhance accountability and traceability in safety-critical decision systems.

Contribution

It proposes a novel compliance-by-construction framework integrating AI, argument graphs, and provenance for verifiable certification evidence.

Findings

Deterministic validation rules prevent unsupported claims.

The architecture supports verifiable, evidence-linked formal arguments.

System design enables AI-assisted argument construction with auditability.

Abstract

High-stakes decision systems increasingly require structured justification, traceability, and auditability to ensure accountability and regulatory compliance. Formal arguments commonly used in the certification of safety-critical systems provide a mechanism for structuring claims, reasoning, and evidence in a verifiable manner. At the same time, generative artificial intelligence systems are increasingly integrated into decision-support workflows, assisting with drafting explanations, summarizing evidence, and generating recommendations. However, current deployments often rely on language models as loosely constrained assistants, which introduces risks such as hallucinated reasoning, unsupported claims, and weak traceability. This paper proposes a compliance-by-construction architecture that integrates Generative AI (GenAI) with structured formal argument representations. The approach treats each AI-assisted step as a claim that must be supported by verifiable evidence and validated against explicit reasoning constraints before it becomes part of an official decision record. The architecture combines four components: i) a typed Argument Graph representation inspired by assurance-case methods, ii) retrieval-augmented generation (RAG) to draft argument fragments grounded in authoritative evidence, iii) a reasoning and validation kernel enforcing completeness and admissibility constraints, and iv) a provenance ledger aligned with the W3C PROV standard to support auditability. We present a system design and an evaluation strategy based on enforceable invariants and worked examples. The analysis suggests that deterministic validation rules can prevent unsupported claims from entering the decision record while allowing GenAI to accelerate argument construction.