Preliminary Quantitative Study on Explainability and Trust in AI Systems
It provides empirical evidence for human-centered explainable AI, addressing trust issues in critical domains like law, healthcare, and finance, but is incremental as it builds on existing research.
This study tackled the problem of how explainability affects user trust in AI systems by conducting a quantitative experiment with a loan approval simulation, finding that interactive explanations enhance user engagement and confidence, with clarity and relevance being key factors.
Large-scale AI models such as GPT-4 have accelerated the deployment of artificial intelligence across critical domains including law, healthcare, and finance, raising urgent questions about trust and transparency. This study investigates the relationship between explainability and user trust in AI systems through a quantitative experimental design. Using an interactive, web-based loan approval simulation, we compare how different types of explanations, ranging from basic feature importance to interactive counterfactuals influence perceived trust. Results suggest that interactivity enhances both user engagement and confidence, and that the clarity and relevance of explanations are key determinants of trust. These findings contribute empirical evidence to the growing field of human-centered explainable AI, highlighting measurable effects of explainability design on user perception