On Representing Humans' Soft-Ethics Preferences As Dispositions
Donatella Donati, Ziba Assadi, Simone Gozzano, Paola Inverardi, Nicolas Troquard
TL;DR
The paper addresses how to preserve humans' soft-ethics preferences when interacting with autonomous systems by modeling these preferences as dispositional properties that are triggered by scenario stimuli. It proposes a dispositional, behaviourist framework in which four interval-scale parameters $p_1$–$p_4$ are elicited via a questionnaire and mapped into a dispositional rule repertoire, with plans to implement these as a software exoskeleton that augments human autonomy. A moral oracle, $soundj$, is introduced to assess the soundness of user justifications before eliciting dispositions, enabling consistent, category-based generalization across scenarios. The work outlines concrete steps for future development, including a formal representation language for soft-ethics dispositions, probabilistic or fuzzy-logical extensions, and automated data extraction to build deployable ethical profiles for autonomous systems.
Abstract
The aim of this paper is to represent humans' soft-ethical preferences by means of dispositional properties. We begin by examining real-life situations, termed as scenarios, that involve ethical dilemmas. Users engage with these scenarios, making decisions on how to act and providing justifications for their choices. We adopt a dispositional approach to represent these scenarios and the interaction with the users. Dispositions are properties that are instantiated by any kind of entity and that may manifest if properly triggered. In particular, the dispositional properties we are interested in are the ethical and behavioural ones. The approach will be described by means of examples. The ultimate goal is to implement the results of this work into a software exoskeleton solution aimed at augmenting human capabilities by preserving their soft-ethical preferences in interactions with autonomous systems.