Explanation-Driven Interventions for Artificial Intelligence Model Customization: Empowering End-Users to Tailor Black-Box AI in Rhinocytology
This addresses the challenge of ensuring human control over AI in critical applications, though it appears incremental as it builds on existing explainability and user control concepts.
The paper tackles the problem of enabling end-users to customize black-box AI models in high-risk domains like rhinocytology by allowing them to edit explanations to influence predictions, advancing Human-Centered AI through a symbiotic human-AI relationship.
The integration of Artificial Intelligence (AI) in modern society is transforming how individuals perform tasks. In high-risk domains, ensuring human control over AI systems remains a key design challenge. This article presents a novel End-User Development (EUD) approach for black-box AI models, enabling users to edit explanations and influence future predictions through targeted interventions. By combining explainability, user control, and model adaptability, the proposed method advances Human-Centered AI (HCAI), promoting a symbiotic relationship between humans and adaptive, user-tailored AI systems.