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

TL;DR

This paper introduces PADTHAI-MM, a principles-based iterative framework leveraging MAST for designing trustworthy, human-centered AI systems, demonstrated through the development and evaluation of the READIT platform for intelligence reporting.

Contribution

It extends MAST into an actionable design methodology for high-stakes AI, validated through empirical evaluation of trust in a specialized intelligence reporting system.

Findings

High-MAST improves trust ratings over Low-MAST.

Stakeholder trust correlates with process, purpose, and performance information.

PADTHAI-MM is effective for context-specific AI design.

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.