Explainable AI Systems Must Be Contestable: Here's How to Make It Happen

• URL: http://arxiv.org/abs/2506.01662v1
• Date: Mon, 02 Jun 2025 13:32:05 GMT
• Title: Explainable AI Systems Must Be Contestable: Here's How to Make It Happen
• Authors: Catarina Moreira, Anna Palatkina, Dacia Braca, Dylan M. Walsh, Peter J. Leihn, Fang Chen, Nina C. Hubig,
• Abstract summary: This paper presents the first rigorous formal definition of contestability in explainable AI.<n>We introduce a modular framework of by-design and post-hoc mechanisms spanning human-centered interfaces, technical processes, and organizational architectures.<n>Our work equips practitioners with the tools to embed genuine recourse and accountability into AI systems.
• Score: 2.5875936082584623
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Agentic AI for Cybersecurity: A Meta-Cognitive Architecture for Governable Autonomy [0.0]
  This paper argues that cybersecurity orchestration should be reconceptualized as an agentic, multi-agent cognitive system.<n>We introduce a conceptual framework in which heterogeneous AI agents responsible for detection, hypothesis formation, contextual interpretation, explanation, and governance are coordinated through an explicit meta-cognitive judgement function.<n>Our contribution is to make this cognitive structure architecturally explicit and governable by embedding meta-cognitive judgement as a first-class system function.
  arXiv  Detail & Related papers  (2026-02-12T12:52:49Z)
• HAIF: A Human-AI Integration Framework for Hybrid Team Operations [0.0]
  The rapid deployment of generative AI, copilots, and agentic systems in knowledge work has created an operational gap.<n>No existing framework addresses how to organize daily work in teams where AI agents perform substantive, delegated tasks alongside humans.<n>This paper proposes the HumanAI Integration Framework (HAIF), a protocol-based, scalable operational system built around four core principles.
  arXiv  Detail & Related papers  (2026-02-07T17:49:53Z)
• Standards for trustworthy AI in the European Union: technical rationale, structural challenges, and an implementation path [0.0]
  This white paper examines the technical foundations of European AI standardization under the AI Act.<n>It explains how harmonized standards enable the presumption of conformity mechanism, describes the CEN/CENELEC standardization process, and analyzes why AI poses unique challenges.
  arXiv  Detail & Related papers  (2026-01-21T11:58:47Z)
• Understanding AI Trustworthiness: A Scoping Review of AIES & FAccT Articles [41.419459280691605]
  Trustworthy AI serves as a foundational pillar for two major AI ethics conferences: AIES and FAccT.<n>This scoping review aims to examine how the AIES and FAccT communities conceptualize, measure, and validate AI trustworthiness.
  arXiv  Detail & Related papers  (2025-10-24T09:40:38Z)
• Safe and Certifiable AI Systems: Concepts, Challenges, and Lessons Learned [45.44933002008943]
  This white paper presents the T"UV AUSTRIA Trusted AI framework.<n>It is an end-to-end audit catalog and methodology for assessing and certifying machine learning systems.<n>Building on three pillars - Secure Software Development, Functional Requirements, and Ethics & Data Privacy - it translates the high-level obligations of the EU AI Act into specific, testable criteria.
  arXiv  Detail & Related papers  (2025-09-08T17:52:08Z)
• Never Compromise to Vulnerabilities: A Comprehensive Survey on AI Governance [211.5823259429128]
  We propose a comprehensive framework integrating technical and societal dimensions, structured around three interconnected pillars: Intrinsic Security, Derivative Security, and Social Ethics.<n>We identify three core challenges: (1) the generalization gap, where defenses fail against evolving threats; (2) inadequate evaluation protocols that overlook real-world risks; and (3) fragmented regulations leading to inconsistent oversight.<n>Our framework offers actionable guidance for researchers, engineers, and policymakers to develop AI systems that are not only robust and secure but also ethically aligned and publicly trustworthy.
  arXiv  Detail & Related papers  (2025-08-12T09:42:56Z)
• Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor [83.99510317617694]
  We argue that a broader conception of what rigorous AI research and practice should entail is needed.<n>We aim to provide useful language and a framework for much-needed dialogue about the AI community's work.
  arXiv  Detail & Related papers  (2025-06-17T15:44:41Z)
• Towards Safety and Security Testing of Cyberphysical Power Systems by Shape Validation [42.350737545269105]
  complexity of cyberphysical power systems leads to larger attack surfaces to be exploited by malicious actors.<n>We propose to meet those risks with a declarative approach to describe cyber power systems and automatically evaluate security and safety controls.
  arXiv  Detail & Related papers  (2025-06-14T12:07:44Z)
• Watermarking Without Standards Is Not AI Governance [46.71493672772134]
  We argue that current implementations risk serving as symbolic compliance rather than delivering effective oversight.<n>We propose a three-layer framework encompassing technical standards, audit infrastructure, and enforcement mechanisms.
  arXiv  Detail & Related papers  (2025-05-27T18:10:04Z)
• Justified Evidence Collection for Argument-based AI Fairness Assurance [7.65321625950609]
  This paper introduces a systems-engineering-driven framework, supported by software tooling, to operationalise a dynamic approach to argument-based assurance in two stages.<n>The framework's effectiveness is demonstrated through an illustrative case study in finance, with a focus on supporting fairness-related arguments.
  arXiv  Detail & Related papers  (2025-05-12T21:05:33Z)
• Compliance of AI Systems [0.0]
  This paper systematically examines the compliance of AI systems with relevant legislation, focusing on the EU's AI Act.<n>The analysis highlighted many challenges associated with edge devices, which are increasingly being used to deploy AI applications closer and closer to the data sources.<n>The importance of data set compliance is highlighted as a cornerstone for ensuring the trustworthiness, transparency, and explainability of AI systems.
  arXiv  Detail & Related papers  (2025-03-07T16:53:36Z)
• Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing Systems [39.23499993745249]
  We introduce semantic integrity constraints (SICs) for specifying and enforcing correctness conditions over LLM outputs in semantic queries.<n>SICs generalize traditional database integrity constraints to semantic settings, supporting common types of constraints, such as grounding, soundness, and exclusion.<n>We present a system design for integrating SICs into query planning and runtime and discuss its realization in AI-augmented DPSs.
  arXiv  Detail & Related papers  (2025-03-01T19:59:25Z)
• A Comprehensive Framework for Reliable Legal AI: Combining Specialized Expert Systems and Adaptive Refinement [0.0]
  Article proposes a novel framework combining expert systems with a knowledge-based architecture to improve the precision and contextual relevance of AI-driven legal services.<n>This framework utilizes specialized modules, each focusing on specific legal areas, and incorporates structured operational guidelines to enhance decision-making.<n>The proposed approach demonstrates significant improvements over existing AI models, showcasing enhanced performance in legal tasks and offering a scalable solution to provide more accessible and affordable legal services.
  arXiv  Detail & Related papers  (2024-12-29T14:00:11Z)
• Using AI Alignment Theory to understand the potential pitfalls of regulatory frameworks [55.2480439325792]
  This paper critically examines the European Union's Artificial Intelligence Act (EU AI Act) Uses insights from Alignment Theory (AT) research, which focuses on the potential pitfalls of technical alignment in Artificial Intelligence. As we apply these concepts to the EU AI Act, we uncover potential vulnerabilities and areas for improvement in the regulation.
  arXiv  Detail & Related papers  (2024-10-10T17:38:38Z)
• Ethical and Scalable Automation: A Governance and Compliance Framework for Business Applications [0.0]
  This paper introduces a framework ensuring that AI must be ethical, controllable, viable, and desirable.<n>Different case studies validate this framework by integrating AI in both academic and practical environments.
  arXiv  Detail & Related papers  (2024-09-25T12:39:28Z)
• How VADER is your AI? Towards a definition of artificial intelligence systems appropriate for regulation [39.58317527488534]
  Recent AI regulation proposals adopt AI definitions affecting ICT techniques, approaches, and systems that are not AI.<n>We propose a framework to score how validated as appropriately-defined for regulation (VADER) an AI definition is.
  arXiv  Detail & Related papers  (2024-02-07T17:41:15Z)
• Towards a Responsible AI Metrics Catalogue: A Collection of Metrics for AI Accountability [28.67753149592534]
  This study bridges the accountability gap by introducing our effort towards a comprehensive metrics catalogue. Our catalogue delineates process metrics that underpin procedural integrity, resource metrics that provide necessary tools and frameworks, and product metrics that reflect the outputs of AI systems.
  arXiv  Detail & Related papers  (2023-11-22T04:43:16Z)
• An interdisciplinary conceptual study of Artificial Intelligence (AI) for helping benefit-risk assessment practices: Towards a comprehensive qualification matrix of AI programs and devices (pre-print 2020) [55.41644538483948]
  This paper proposes a comprehensive analysis of existing concepts coming from different disciplines tackling the notion of intelligence. The aim is to identify shared notions or discrepancies to consider for qualifying AI systems.
  arXiv  Detail & Related papers  (2021-05-07T12:01:31Z)
• Towards an Interface Description Template for AI-enabled Systems [77.34726150561087]
  Reuse is a common system architecture approach that seeks to instantiate a system architecture with existing components. There is currently no framework that guides the selection of necessary information to assess their portability to operate in a system different than the one for which the component was originally purposed. We present ongoing work on establishing an interface description template that captures the main information of an AI-enabled component.
  arXiv  Detail & Related papers  (2020-07-13T20:30:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.