Towards a Novel Measure of User Trust in XAI Systems
This addresses the need for better trust assessment in XAI for end-users, though it appears incremental as it builds on existing trust measurement approaches.
The paper tackles the problem of measuring user trust in XAI systems by proposing a novel metric that combines performance and trust indicators, showing improvements over state-of-the-art methods in three case studies with increased sensitivity to scenarios.
The increasing reliance on Deep Learning models, combined with their inherent lack of transparency, has spurred the development of a novel field of study known as eXplainable AI (XAI) methods. These methods seek to enhance the trust of end-users in automated systems by providing insights into the rationale behind their decisions. This paper presents a novel trust measure in XAI systems, allowing their refinement. Our proposed metric combines both performance metrics and trust indicators from an objective perspective. To validate this novel methodology, we conducted three case studies showing an improvement respect the state-of-the-art, with an increased sensitiviy to different scenarios.