Assessing Model-Agnostic XAI Methods against EU AI Act Explainability Requirements

• URL: http://arxiv.org/abs/2604.09628v1
• Date: Thu, 19 Mar 2026 09:32:07 GMT
• Title: Assessing Model-Agnostic XAI Methods against EU AI Act Explainability Requirements
• Abstract summary: We study model-agnostic XAI methods and relate their interpretability features to the requirements of the AI Act.<n>We then propose a qualitative-to-quantitative scoring framework: expert assessments of XAI properties are aggregated into a regulation-specific compliance score.
• Score: 1.376408511310322
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Explainable AI (XAI) has evolved in response to expectations and regulations, such as the EU AI Act, which introduces regulatory requirements on AI-powered systems. However, a persistent gap remains between existing XAI methods and society's legal requirements, leaving practitioners without clear guidance on how to approach compliance in the EU market. To bridge this gap, we study model-agnostic XAI methods and relate their interpretability features to the requirements of the AI Act. We then propose a qualitative-to-quantitative scoring framework: qualitative expert assessments of XAI properties are aggregated into a regulation-specific compliance score. This helps practitioners identify when XAI solutions may support legal explanation requirements while highlighting technical issues that require further research and regulatory clarification.

Related papers

• Security, privacy, and agentic AI in a regulatory view: From definitions and distinctions to provisions and reflections [53.468443050795344]
  The rapid proliferation of artificial intelligence (AI) technologies has led to a dynamic regulatory landscape.<n>As AI paradigms shift towards greater autonomy, specifically in the form of agentic AI, it becomes increasingly challenging to articulate regulatory stipulations.<n>This paper reviews the evolving European Union (EU) AI regulatory provisions via analyzing 24 relevant documents published between 2024 and 2025.
  arXiv  Detail & Related papers  (2026-03-19T13:50:52Z)
• Argumentation-Based Explainability for Legal AI: Comparative and Regulatory Perspectives [0.9668407688201359]
  Artificial Intelligence (AI) systems are increasingly deployed in legal contexts.<n>The so-called black box problem'' undermines legitimacy of automated decision-making.<n>XAI has proposed a variety of methods to enhance transparency.
  arXiv  Detail & Related papers  (2025-10-13T07:19:15Z)
• The EU AI Act, Stakeholder Needs, and Explainable AI: Aligning Regulatory Compliance in a Clinical Decision Support System [5.6739502570965765]
  XAI aims to enhance transparency and human oversight of AI systems.<n>The AI Act focuses on the obligations of the provider and deployer of the AI system.<n>We show that XAI techniques can fill a gap between stakeholder needs and the requirements of the AI Act.
  arXiv  Detail & Related papers  (2025-05-22T07:39:04Z)
• Unlocking the Black Box: Analysing the EU Artificial Intelligence Act's Framework for Explainability in AI [0.0]
  The need for eXplainable AI (XAI) is evident in fields such as healthcare, credit scoring, policing and the criminal justice system.<n>At the EU level, the notion of explainability is one of the fundamental principles that underpin the AI Act.<n>This paper explores various approaches and techniques that promise to advance XAI, as well as the challenges of implementing the principle of explainability in AI governance and policies.
  arXiv  Detail & Related papers  (2025-01-24T16:30:19Z)
• The explanation dialogues: an expert focus study to understand requirements towards explanations within the GDPR [47.06917254695738]
  We present the Explanation Dialogues, an expert focus study to uncover the expectations, reasoning, and understanding of legal experts and practitioners towards XAI.<n>The study consists of an online questionnaire and follow-up interviews, and is centered around a use-case in the credit domain.<n>We find that the presented explanations are hard to understand and lack information, and discuss issues that can arise from the different interests of the data controller and subject.
  arXiv  Detail & Related papers  (2025-01-09T15:50:02Z)
• COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act [40.233017376716305]
  The EU's Artificial Intelligence Act (AI Act) is a significant step towards responsible AI development.<n>It lacks clear technical interpretation, making it difficult to assess models' compliance.<n>This work presents COMPL-AI, a comprehensive framework consisting of the first technical interpretation of the Act.
  arXiv  Detail & Related papers  (2024-10-10T14:23:51Z)
• The Dilemma of Uncertainty Estimation for General Purpose AI in the EU AI Act [6.9060054915724]
  The AI act is the European Union-wide regulation of AI systems. We argue that uncertainty estimation should be a required component for deploying models in the real world.
  arXiv  Detail & Related papers  (2024-08-20T23:59:51Z)
• How should AI decisions be explained? Requirements for Explanations from the Perspective of European Law [0.20971479389679337]
  This paper focuses on European (and part German) law, although with international concepts and regulations. Based on XAI-taxonomies, requirements for XAI (methods) are derived from each of the legal bases.
  arXiv  Detail & Related papers  (2024-04-19T10:08:28Z)
• Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness [53.91018508439669]
  The study explores the complexities of integrating Artificial Intelligence into Autonomous Vehicles (AVs) It examines the challenges introduced by AI components and the impact on testing procedures. The paper identifies significant challenges and suggests future directions for research and development of AI in AV technology.
  arXiv  Detail & Related papers  (2024-02-21T08:29:42Z)
• Bridging the Transparency Gap: What Can Explainable AI Learn From the AI Act? [0.8287206589886881]
  European Union has introduced detailed requirements of transparency for AI systems. There is a fundamental difference between XAI and the Act regarding what transparency is. By comparing the disparate views of XAI and regulation, we arrive at four axes where practical work could bridge the transparency gap.
  arXiv  Detail & Related papers  (2023-02-21T16:06:48Z)
• Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI [65.44737844681256]
  A lack of consensus on how to evaluate explainable AI (XAI) hinders the advancement of the field. We argue that one way to close the gap is to develop evaluation methods that account for different user requirements.
  arXiv  Detail & Related papers  (2022-06-22T05:17:33Z)
• Fairness in Agreement With European Values: An Interdisciplinary Perspective on AI Regulation [61.77881142275982]
  This interdisciplinary position paper considers various concerns surrounding fairness and discrimination in AI, and discusses how AI regulations address them. We first look at AI and fairness through the lenses of law, (AI) industry, sociotechnology, and (moral) philosophy, and present various perspectives. We identify and propose the roles AI Regulation should take to make the endeavor of the AI Act a success in terms of AI fairness concerns.
  arXiv  Detail & Related papers  (2022-06-08T12:32:08Z)
• 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)

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.