Bridging the Disciplinary Gap in Explainable AI: From Abstract Desiderata to Concrete Tasks

2026-05-19

AI Summary

This study addresses the fragmentation and lack of operationalizability in explainable artificial intelligence (XAI) research, which often stems from difficulties in reconciling abstract, cross-disciplinary desiderata such as fairness and accountability. To bridge this gap, the authors propose a dependency-structured perspective that systematically decomposes high-level XAI objectives into concrete, benchmarkable tasks. They introduce a three-axis taxonomy—encompassing goals, functional roles, and justification modes—and a three-step task design framework. Through systematic literature review and conceptual analysis, this approach clarifies the substantive meaning of normative expectations, reveals interdependencies among explanatory attributes, delineates feasible design spaces, and guides the construction of evaluable XAI tasks. This work represents the first systematic translation of abstract XAI principles into actionable research tasks.

Abstract

Explainable AI (XAI) is often criticized for failing to satisfy broad desiderata (e.g., fairness, accountability) and for limited practical value to stakeholders. This challenge partly arises because researchers across disciplines prioritize different sets of desiderata that remain underspecified and context-dependent, yet expect XAI to satisfy them simultaneously, resulting in fragmented and sometimes incompatible operationalizations. We argue that many desiderata are not independent, but instead form dependency structures in which higher-level goals (\emph{e.g.}, trust, accountability) rely on more foundational properties (\emph{e.g.}, faithfulness, robustness). Some desiderata are multi-faceted and are best understood within these structures. In particular, instead of addressing all desiderata at once, we focus on subsets of dependency structures and translate them into concrete XAI tasks, thereby decomposing research questions into benchmarkable and solvable units. To this end, we propose a three-axis taxonomy (\emph{target}, \emph{functional role}, and \emph{mode of justification}) and a three-step framework for deriving well-scoped, benchmarkable XAI tasks. Our approach builds on a systematic literature review and conceptual analysis, and supports clarifying desiderata, identifying dependencies, scoping feasibility, and delimiting the design space to derive concrete XAI tasks from abstract desiderata. We illustrate its utility through two explanatory cases, showing how the taxonomy and framework guide systematic task design and evaluation in XAI. {\color{red}{This is a preprint of a paper that will appear in AISoLA 2026.}}

Problem

• Explainable AI
• desiderata
• interdisciplinary gap
• accountability
• trust

Innovation

• Explainable AI
• desiderata decomposition
• dependency structure
• taxonomy
• benchmarkable tasks