Towards a Framework for Operationalizing the Specification of Trustworthy AI Requirements

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Villamizar, Hugo, Mendez, Daniel, Kalinowski, Marcos
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916842765811712
author Villamizar, Hugo
Mendez, Daniel
Kalinowski, Marcos
author_facet Villamizar, Hugo
Mendez, Daniel
Kalinowski, Marcos
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_10228
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards a Framework for Operationalizing the Specification of Trustworthy AI Requirements
Villamizar, Hugo
Mendez, Daniel
Kalinowski, Marcos
Software Engineering
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.
title Towards a Framework for Operationalizing the Specification of Trustworthy AI Requirements
topic Software Engineering
url https://arxiv.org/abs/2507.10228