Increasing AI Explainability by LLM Driven Standard Processes
Marc Jansen, Marcel Pehlke
TL;DR
The paper tackles the opacity of AI decision-making by embedding LLM reasoning within standardized, transparent analytical processes. It presents a layered architecture with an Explainability Barrier that elevates rationale from the opaque LLM layer to an upper layer of formal processes (QOC, Sensitivity Analysis, Game Theory, Risk Management). Through empirical evaluations in DAO investment decisions, logistics analysis, and crisis simulation, the approach demonstrates human-like reasoning while delivering auditable, interpretable outputs. The findings suggest LLM-driven standard processes can support reliable, auditable AI-assisted decisions, offering a pathway toward transparent and governance-aligned AI systems for complex domains.
Abstract
This paper introduces an approach to increasing the explainability of artificial intelligence (AI) systems by embedding Large Language Models (LLMs) within standardized analytical processes. While traditional explainable AI (XAI) methods focus on feature attribution or post-hoc interpretation, the proposed framework integrates LLMs into defined decision models such as Question-Option-Criteria (QOC), Sensitivity Analysis, Game Theory, and Risk Management. By situating LLM reasoning within these formal structures, the approach transforms opaque inference into transparent and auditable decision traces. A layered architecture is presented that separates the reasoning space of the LLM from the explainable process space above it. Empirical evaluations show that the system can reproduce human-level decision logic in decentralized governance, systems analysis, and strategic reasoning contexts. The results suggest that LLM-driven standard processes provide a foundation for reliable, interpretable, and verifiable AI-supported decision making.