Towards a Framework for Operationalizing the Specification of Trustworthy AI Requirements

TL;DR

This paper proposes a combined framework integrating artefact-based requirements engineering and perspective-based methods to better specify and operationalize trustworthiness requirements in AI systems, especially ML-enabled ones.

Contribution

It introduces a novel integration of AMDiRE and PerSpecML approaches to address the challenges of specifying trustworthiness in AI systems, bridging stakeholder concerns and structured models.

Findings

Combines structured artefact approach with multi-perspective guidance.

Addresses the non-deterministic behavior of ML-enabled systems.

Outlines future research directions and open challenges.

Abstract

Growing concerns around the trustworthiness of AI-enabled systems highlight the role of requirements engineering (RE) in addressing emergent, context-dependent properties that are difficult to specify without structured approaches. In this short vision paper, we propose the integration of two complementary approaches: AMDiRE, an artefact-based approach for RE, and PerSpecML, a perspective-based method designed to support the elicitation, analysis, and specification of machine learning (ML)-enabled systems. AMDiRE provides a structured, artefact-centric, process-agnostic methodology and templates that promote consistency and traceability in the results; however, it is primarily oriented toward deterministic systems. PerSpecML, in turn, introduces multi-perspective guidance to uncover concerns arising from the data-driven and non-deterministic behavior of ML-enabled systems. We envision a pathway to operationalize trustworthiness-related requirements, bridging stakeholder-driven concerns and structured artefact models. We conclude by outlining key research directions and open challenges to be discussed with the RE community.