Trust in Transparency: How Explainable AI Shapes User Perceptions

TL;DR

This paper argues that trust in AI-powered loan decisions cannot be achieved through algorithmic transparency alone. It proposes contextual explanations that incorporate social, economic, and individual factors, evaluated through COP-12 metrics. The authors conduct a qualitative study with seven participants using a React/Llama-based system and a SHAP-driven explanation solver to compare no, basic, detailed, and interactive explanations. They find that contextual, interactive explanations improve trust and highlight gaps in COP-12, advocating sociotechnical design and framework refinements to support real-world, user-centered explanations.

Abstract

This study explores the integration of contextual explanations into AI-powered loan decision systems to enhance trust and usability. While traditional AI systems rely heavily on algorithmic transparency and technical accuracy, they often fail to account for broader social and economic contexts. Through a qualitative study, I investigated user interactions with AI explanations and identified key gaps, in- cluding the inability of current systems to provide context. My findings underscore the limitations of purely technical transparency and the critical need for contex- tual explanations that bridge the gap between algorithmic outputs and real-world decision-making. By aligning explanations with user needs and broader societal factors, the system aims to foster trust, improve decision-making, and advance the design of human-centered AI systems