Explainability Auditing for Intelligent Systems: A Rationale for Multi-Disciplinary Perspectives
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2021
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913799721713664 |
|---|---|
| author | Langer, Markus Baum, Kevin Hartmann, Kathrin Hessel, Stefan Speith, Timo Wahl, Jonas |
| author_facet | Langer, Markus Baum, Kevin Hartmann, Kathrin Hessel, Stefan Speith, Timo Wahl, Jonas |
| contents | National and international guidelines for trustworthy artificial intelligence (AI) consider explainability to be a central facet of trustworthy systems. This paper outlines a multi-disciplinary rationale for explainability auditing. Specifically, we propose that explainability auditing can ensure the quality of explainability of systems in applied contexts and can be the basis for certification as a means to communicate whether systems meet certain explainability standards and requirements. Moreover, we emphasize that explainability auditing needs to take a multi-disciplinary perspective, and we provide an overview of four perspectives (technical, psychological, ethical, legal) and their respective benefits with respect to explainability auditing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2108_07711 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Explainability Auditing for Intelligent Systems: A Rationale for Multi-Disciplinary Perspectives Langer, Markus Baum, Kevin Hartmann, Kathrin Hessel, Stefan Speith, Timo Wahl, Jonas Computers and Society National and international guidelines for trustworthy artificial intelligence (AI) consider explainability to be a central facet of trustworthy systems. This paper outlines a multi-disciplinary rationale for explainability auditing. Specifically, we propose that explainability auditing can ensure the quality of explainability of systems in applied contexts and can be the basis for certification as a means to communicate whether systems meet certain explainability standards and requirements. Moreover, we emphasize that explainability auditing needs to take a multi-disciplinary perspective, and we provide an overview of four perspectives (technical, psychological, ethical, legal) and their respective benefits with respect to explainability auditing. |
| title | Explainability Auditing for Intelligent Systems: A Rationale for Multi-Disciplinary Perspectives |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2108.07711 |