Justified Evidence Collection for Argument-based AI Fairness Assurance

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sabuncuoglu, Alpay, Burr, Christopher, Maple, Carsten
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913834243981312
author Sabuncuoglu, Alpay
Burr, Christopher
Maple, Carsten
author_facet Sabuncuoglu, Alpay
Burr, Christopher
Maple, Carsten
contents It is well recognised that ensuring fair AI systems is a complex sociotechnical challenge, which requires careful deliberation and continuous oversight across all stages of a system's lifecycle, from defining requirements to model deployment and deprovisioning. Dynamic argument-based assurance cases, which present structured arguments supported by evidence, have emerged as a systematic approach to evaluating and mitigating safety risks and hazards in AI-enabled system development and have also been extended to deal with broader normative goals such as fairness and explainability. This paper introduces a systems-engineering-driven framework, supported by software tooling, to operationalise a dynamic approach to argument-based assurance in two stages. In the first stage, during the requirements planning phase, a multi-disciplinary and multi-stakeholder team define goals and claims to be established (and evidenced) by conducting a comprehensive fairness governance process. In the second stage, a continuous monitoring interface gathers evidence from existing artefacts (e.g. metrics from automated tests), such as model, data, and use case documentation, to support these arguments dynamically. The framework's effectiveness is demonstrated through an illustrative case study in finance, with a focus on supporting fairness-related arguments.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08064
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Justified Evidence Collection for Argument-based AI Fairness Assurance
Sabuncuoglu, Alpay
Burr, Christopher
Maple, Carsten
Human-Computer Interaction
Artificial Intelligence
Computers and Society
It is well recognised that ensuring fair AI systems is a complex sociotechnical challenge, which requires careful deliberation and continuous oversight across all stages of a system's lifecycle, from defining requirements to model deployment and deprovisioning. Dynamic argument-based assurance cases, which present structured arguments supported by evidence, have emerged as a systematic approach to evaluating and mitigating safety risks and hazards in AI-enabled system development and have also been extended to deal with broader normative goals such as fairness and explainability. This paper introduces a systems-engineering-driven framework, supported by software tooling, to operationalise a dynamic approach to argument-based assurance in two stages. In the first stage, during the requirements planning phase, a multi-disciplinary and multi-stakeholder team define goals and claims to be established (and evidenced) by conducting a comprehensive fairness governance process. In the second stage, a continuous monitoring interface gathers evidence from existing artefacts (e.g. metrics from automated tests), such as model, data, and use case documentation, to support these arguments dynamically. The framework's effectiveness is demonstrated through an illustrative case study in finance, with a focus on supporting fairness-related arguments.
title Justified Evidence Collection for Argument-based AI Fairness Assurance
topic Human-Computer Interaction
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2505.08064