Explanation-Driven Interventions for Artificial Intelligence Model Customization: Empowering End-Users to Tailor Black-Box AI in Rhinocytology
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912394189471744 |
|---|---|
| author | Esposito, Andrea Calvano, Miriana Curci, Antonio Greco, Francesco Lanzilotti, Rosa Piccinno, Antonio |
| author_facet | Esposito, Andrea Calvano, Miriana Curci, Antonio Greco, Francesco Lanzilotti, Rosa Piccinno, Antonio |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04833 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Explanation-Driven Interventions for Artificial Intelligence Model Customization: Empowering End-Users to Tailor Black-Box AI in Rhinocytology Esposito, Andrea Calvano, Miriana Curci, Antonio Greco, Francesco Lanzilotti, Rosa Piccinno, Antonio Human-Computer Interaction Artificial Intelligence 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. |
| title | Explanation-Driven Interventions for Artificial Intelligence Model Customization: Empowering End-Users to Tailor Black-Box AI in Rhinocytology |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2504.04833 |