Modelling GDPR-Compliant Explanations for Trustworthy AI

TL;DR

This paper introduces Explanatory Narratives (EN), a user-centered model for generating GDPR-compliant explanations of AI decisions, enabling interactive exploration tailored to user needs.

Contribution

It proposes a novel EN model based on ISO standards, transforming explanation generation into navigating an Explanatory Space for personalized, compliant AI explanations.

Findings

EN enables interactive, user-centered explanations.

The model aligns with GDPR and AI-HLEG guidelines.

Analysis of EN's strengths and weaknesses.

Abstract

Through the General Data Protection Regulation (GDPR), the European Union has set out its vision for Automated Decision- Making (ADM) and AI, which must be reliable and human-centred. In particular we are interested on the Right to Explanation, that requires industry to produce explanations of ADM. The High-Level Expert Group on Artificial Intelligence (AI-HLEG), set up to support the implementation of this vision, has produced guidelines discussing the types of explanations that are appropriate for user-centred (interactive) Explanatory Tools. In this paper we propose our version of Explanatory Narratives (EN), based on user-centred concepts drawn from ISO 9241, as a model for user-centred explanations aligned with the GDPR and the AI-HLEG guidelines. Through the use of ENs we convert the problem of generating explanations for ADM into the identification of an appropriate path over an Explanatory Space, allowing explainees to interactively explore it and produce the explanation best suited to their needs. To this end we list suitable exploration heuristics, we study the properties and structure of explanations, and discuss the proposed model identifying its weaknesses and strengths.