Explainable AI Systems Must Be Contestable: Here's How to Make It Happen
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_ | 1866918042926055424 |
|---|---|
| author | Moreira, Catarina Palatkina, Anna Braca, Dacia Walsh, Dylan M. Leihn, Peter J. Chen, Fang Hubig, Nina C. |
| author_facet | Moreira, Catarina Palatkina, Anna Braca, Dacia Walsh, Dylan M. Leihn, Peter J. Chen, Fang Hubig, Nina C. |
| contents | As AI regulations around the world intensify their focus on system safety, contestability has become a mandatory, yet ill-defined, safeguard. In XAI, "contestability" remains an empty promise: no formal definition exists, no algorithm guarantees it, and practitioners lack concrete guidance to satisfy regulatory requirements. Grounded in a systematic literature review, this paper presents the first rigorous formal definition of contestability in explainable AI, directly aligned with stakeholder requirements and regulatory mandates. We introduce a modular framework of by-design and post-hoc mechanisms spanning human-centered interfaces, technical architectures, legal processes, and organizational workflows. To operationalize our framework, we propose the Contestability Assessment Scale, a composite metric built on more than twenty quantitative criteria. Through multiple case studies across diverse application domains, we reveal where state-of-the-art systems fall short and show how our framework drives targeted improvements. By converting contestability from regulatory theory into a practical framework, our work equips practitioners with the tools to embed genuine recourse and accountability into AI systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01662 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Explainable AI Systems Must Be Contestable: Here's How to Make It Happen Moreira, Catarina Palatkina, Anna Braca, Dacia Walsh, Dylan M. Leihn, Peter J. Chen, Fang Hubig, Nina C. Computers and Society Artificial Intelligence Machine Learning As AI regulations around the world intensify their focus on system safety, contestability has become a mandatory, yet ill-defined, safeguard. In XAI, "contestability" remains an empty promise: no formal definition exists, no algorithm guarantees it, and practitioners lack concrete guidance to satisfy regulatory requirements. Grounded in a systematic literature review, this paper presents the first rigorous formal definition of contestability in explainable AI, directly aligned with stakeholder requirements and regulatory mandates. We introduce a modular framework of by-design and post-hoc mechanisms spanning human-centered interfaces, technical architectures, legal processes, and organizational workflows. To operationalize our framework, we propose the Contestability Assessment Scale, a composite metric built on more than twenty quantitative criteria. Through multiple case studies across diverse application domains, we reveal where state-of-the-art systems fall short and show how our framework drives targeted improvements. By converting contestability from regulatory theory into a practical framework, our work equips practitioners with the tools to embed genuine recourse and accountability into AI systems. |
| title | Explainable AI Systems Must Be Contestable: Here's How to Make It Happen |
| topic | Computers and Society Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2506.01662 |