PADTHAI-MM: Principles-based Approach for Designing Trustworthy, Human-centered AI using MAST Methodology

TL;DR

The paper tackles the challenge of designing trustworthy AI in high-stakes domains by introducing PADTHAI-MM, a Principles-based Approach for Designing Trustworthy, Human-centered AI using MAST Methodology, which translates MAST tradecraft criteria into concrete design steps. It validates the framework through READIT, an NLP-assisted intelligence reporting platform, by comparing High-MAST and Low-MAST iterations and showing that High-MAST designs yield stronger trust ratings across multiple dimensions. Theoretical validation connects MAST-derived design features to perceived trust via matrices, PCA, and regression analyses, demonstrating meaningful links between design choices and user trust. Practically, PADTHAI-MM offers a viable, domain-informed design methodology that aligns system functionality with trust requirements, with potential applicability beyond intelligence analytics to other high-stakes AI-DSS contexts.

Abstract

Despite an extensive body of literature on trust in technology, designing trustworthy AI systems for high-stakes decision domains remains a significant challenge, further compounded by the lack of actionable design and evaluation tools. The Multisource AI Scorecard Table (MAST) was designed to bridge this gap by offering a systematic, tradecraft-centered approach to evaluating AI-enabled decision support systems. Expanding on MAST, we introduce an iterative design framework called \textit{Principles-based Approach for Designing Trustworthy, Human-centered AI using MAST Methodology} (PADTHAI-MM). We demonstrate this framework in our development of the Reporting Assistant for Defense and Intelligence Tasks (READIT), a research platform that leverages data visualizations and natural language processing-based text analysis, emulating an AI-enabled system supporting intelligence reporting work. To empirically assess the efficacy of MAST on trust in AI, we developed two distinct iterations of READIT for comparison: a High-MAST version, which incorporates AI contextual information and explanations, and a Low-MAST version, akin to a ``black box'' system. This iterative design process, guided by stakeholder feedback and contemporary AI architectures, culminated in a prototype that was evaluated through its use in an intelligence reporting task. We further discuss the potential benefits of employing the MAST-inspired design framework to address context-specific needs. We also explore the relationship between stakeholder evaluators' MAST ratings and three categories of information known to impact trust: \textit{process}, \textit{purpose}, and \textit{performance}. Overall, our study supports the practical benefits and theoretical validity for PADTHAI-MM as a viable method for designing trustable, context-specific AI systems.

Figures (3)

• Figure 1: PADTHAI-MM Design Framework
• Figure 2: PCA loadings for three dimensions in trust theory
• Figure 3: Principal Component Regression results