---
_id: '62028'
abstract:
- lang: eng
  text: 'Explainable AI (XAI) methods can support the identification of biases in
    automated decision-making (ADM) systems. However, existing research does not sufficiently
    address whether these biases originate from the ADM system or mirror underlying
    societal inequalities. This distinction is important because it has major implications
    for how to act upon an explanation: while the societal bias produced by the ADM
    system can be algorithmically fixed, societal inequalities demand societal actions.
    To address this gap, we propose the RR-XAI-framework (recognition-redistribution
    through XAI) that builds on a distinction between socio-technical and societal
    bias and Nancy Fraser''s justice theory of recognition and redistribution. In
    our framework, explanations can play two distinct roles: as a socio-technical
    diagnosis when they reveal biases produced by the ADM system itself, or as a societal
    diagnosis when they expose biases that reflect broader societal inequalities.
    We then outline the operationalization of the framework and discuss its applicability
    for cases in algorithmic hiring and credit scoring. Based on our findings, we
    argue that the diagnostic functions of XAI are contingent on the provision of
    such explanations, the resources of the audiences, as well as the current limits
    of XAI techniques.'
article_type: original
author:
- first_name: Miriam
  full_name: Fahimi, Miriam
  id: '118059'
  last_name: Fahimi
  orcid: 0000-0002-0619-3160
- first_name: Laura
  full_name: State, Laura
  last_name: State
- first_name: Atoosa
  full_name: Kasirzadeh, Atoosa
  last_name: Kasirzadeh
citation:
  ama: 'Fahimi M, State L, Kasirzadeh A. From Explaining to Diagnosing: A Justice-Oriented
    Framework of Explainable AI for Bias Detection. <i>Proceedings of the AAAI/ACM
    Conference on AI, Ethics, and Society</i>. 2025;8(1):879-892. doi:<a href="https://doi.org/10.1609/aies.v8i1.36597">10.1609/aies.v8i1.36597</a>'
  apa: 'Fahimi, M., State, L., &#38; Kasirzadeh, A. (2025). From Explaining to Diagnosing:
    A Justice-Oriented Framework of Explainable AI for Bias Detection. <i>Proceedings
    of the AAAI/ACM Conference on AI, Ethics, and Society</i>, <i>8</i>(1), 879–892.
    <a href="https://doi.org/10.1609/aies.v8i1.36597">https://doi.org/10.1609/aies.v8i1.36597</a>'
  bibtex: '@article{Fahimi_State_Kasirzadeh_2025, title={From Explaining to Diagnosing:
    A Justice-Oriented Framework of Explainable AI for Bias Detection}, volume={8},
    DOI={<a href="https://doi.org/10.1609/aies.v8i1.36597">10.1609/aies.v8i1.36597</a>},
    number={1}, journal={Proceedings of the AAAI/ACM Conference on AI, Ethics, and
    Society}, publisher={Association for the Advancement of Artificial Intelligence
    (AAAI)}, author={Fahimi, Miriam and State, Laura and Kasirzadeh, Atoosa}, year={2025},
    pages={879–892} }'
  chicago: 'Fahimi, Miriam, Laura State, and Atoosa Kasirzadeh. “From Explaining to
    Diagnosing: A Justice-Oriented Framework of Explainable AI for Bias Detection.”
    <i>Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society</i> 8, no.
    1 (2025): 879–92. <a href="https://doi.org/10.1609/aies.v8i1.36597">https://doi.org/10.1609/aies.v8i1.36597</a>.'
  ieee: 'M. Fahimi, L. State, and A. Kasirzadeh, “From Explaining to Diagnosing: A
    Justice-Oriented Framework of Explainable AI for Bias Detection,” <i>Proceedings
    of the AAAI/ACM Conference on AI, Ethics, and Society</i>, vol. 8, no. 1, pp.
    879–892, 2025, doi: <a href="https://doi.org/10.1609/aies.v8i1.36597">10.1609/aies.v8i1.36597</a>.'
  mla: 'Fahimi, Miriam, et al. “From Explaining to Diagnosing: A Justice-Oriented
    Framework of Explainable AI for Bias Detection.” <i>Proceedings of the AAAI/ACM
    Conference on AI, Ethics, and Society</i>, vol. 8, no. 1, Association for the
    Advancement of Artificial Intelligence (AAAI), 2025, pp. 879–92, doi:<a href="https://doi.org/10.1609/aies.v8i1.36597">10.1609/aies.v8i1.36597</a>.'
  short: M. Fahimi, L. State, A. Kasirzadeh, Proceedings of the AAAI/ACM Conference
    on AI, Ethics, and Society 8 (2025) 879–892.
date_created: 2025-10-31T15:05:38Z
date_updated: 2025-11-18T10:09:40Z
department:
- _id: '756'
- _id: '26'
doi: 10.1609/aies.v8i1.36597
intvolume: '         8'
issue: '1'
language:
- iso: eng
page: 879-892
publication: Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society
publication_identifier:
  issn:
  - 3065-8365
publication_status: published
publisher: Association for the Advancement of Artificial Intelligence (AAAI)
status: public
title: 'From Explaining to Diagnosing: A Justice-Oriented Framework of Explainable
  AI for Bias Detection'
type: journal_article
user_id: '118059'
volume: 8
year: '2025'
...